File: //var/log/sd-webui.log
################################################################
[1m[32mInstall script for stable-diffusion + Web UI
[1m[34mTested on Debian 11 (Bullseye), Fedora 34+ and openSUSE Leap 15.4 or newer.[0m
################################################################
################################################################
Running on [1m[32mroot[0m user
################################################################
################################################################
Repo already cloned, using it as install directory
################################################################
################################################################
Create and activate python venv
################################################################
################################################################
Launching launch.py...
################################################################
glibc version is 2.39
Check TCMalloc: libtcmalloc_minimal.so.4
libtcmalloc_minimal.so.4 is linked with libc.so,execute LD_PRELOAD=/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4
=============================================================================================
INCOMPATIBLE PYTHON VERSION
This program is tested with 3.10.6 Python, but you have 3.12.3.
If you encounter an error with "RuntimeError: Couldn't install torch." message,
or any other error regarding unsuccessful package (library) installation,
please downgrade (or upgrade) to the latest version of 3.10 Python
and delete current Python and "venv" folder in WebUI's directory.
You can download 3.10 Python from here: https://www.python.org/downloads/release/python-3106/
Use --skip-python-version-check to suppress this warning.
=============================================================================================
Python 3.12.3 (main, Jan 22 2026, 20:57:42) [GCC 13.3.0]
Version: f2.0.1v1.10.1-previous-669-gdfdcbab6
Commit hash: dfdcbab685e57677014f05a3309b48cc87383167
Legacy Preprocessor init warning: Unable to install insightface automatically. Please try run `pip install insightface` manually.
Launching Web UI with arguments: -f --listen --api --enable-insecure-extension-access --xformers --no-half-vae --port 7887
/opt/sd-webui/venv/lib/python3.12/site-packages/torch/cuda/__init__.py:619: UserWarning: Can't initialize NVML
warnings.warn("Can't initialize NVML")
Total VRAM 20017 MB, total RAM 64105 MB
pytorch version: 2.3.1+cu121
WARNING:xformers:A matching Triton is not available, some optimizations will not be enabled
Traceback (most recent call last):
File "/opt/sd-webui/venv/lib/python3.12/site-packages/xformers/__init__.py", line 57, in _is_triton_available
import triton # noqa
^^^^^^^^^^^^^
ModuleNotFoundError: No module named 'triton'
xformers version: 0.0.27
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA RTX 4000 SFF Ada Generation : native
Hint: your device supports --cuda-malloc for potential speed improvements.
VAE dtype preferences: [torch.bfloat16, torch.float32] -> torch.bfloat16
CUDA Using Stream: False
Using xformers cross attention
Using xformers attention for VAE
ControlNet preprocessor location: /opt/sd-webui/models/ControlNetPreprocessor
*** Error loading script: soft_inpainting.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 525, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/sd-webui/modules/script_loading.py", line 13, in load_module
module_spec.loader.exec_module(module)
File "<frozen importlib._bootstrap_external>", line 995, in exec_module
File "<frozen importlib._bootstrap>", line 488, in _call_with_frames_removed
File "/opt/sd-webui/extensions-builtin/soft-inpainting/scripts/soft_inpainting.py", line 10, in <module>
from joblib import Parallel, delayed, cpu_count
ModuleNotFoundError: No module named 'joblib'
---
2026-02-06 21:52:56,817 - ControlNet - [0;32mINFO[0m - ControlNet UI callback registered.
Model selected: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
Using online LoRAs in FP16: False
Running on local URL: http://0.0.0.0:7887
To create a public link, set `share=True` in `launch()`.
Startup time: 9.8s (prepare environment: 1.7s, launcher: 0.3s, import torch: 4.2s, other imports: 0.2s, load scripts: 0.9s, create ui: 1.2s, gradio launch: 0.5s, add APIs: 0.8s).
Loading Model: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Done.
StateDict Keys: {'unet': 1680, 'vae': 248, 'text_encoder': 197, 'text_encoder_2': 518, 'ignore': 0}
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
K-Model Created: {'storage_dtype': torch.float16, 'computation_dtype': torch.float16}
Model loaded in 0.9s (unload existing model: 0.1s, forge model load: 0.8s).
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3051.58 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 18504.96 MB, Model Require: 1559.68 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 15921.28 MB, All loaded to GPU.
Moving model(s) has taken 1.11 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 16701.26 MB ... Done.
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 16700.58 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 16700.58 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 10779.53 MB, All loaded to GPU.
Moving model(s) has taken 3.42 seconds
0%| | 0/20 [00:00<?, ?it/s]
Total progress: 0%| | 0/20 [00:00<?, ?it/s][A
5%|▌ | 1/20 [00:00<00:07, 2.62it/s]
Total progress: 15%|█▌ | 3/20 [00:00<00:00, 21.25it/s][A
15%|█▌ | 3/20 [00:00<00:02, 5.95it/s]
25%|██▌ | 5/20 [00:00<00:01, 7.66it/s]
Total progress: 30%|███ | 6/20 [00:00<00:01, 13.27it/s][A
35%|███▌ | 7/20 [00:00<00:01, 8.59it/s]
Total progress: 40%|████ | 8/20 [00:00<00:01, 12.00it/s][A
45%|████▌ | 9/20 [00:01<00:01, 9.11it/s]
Total progress: 50%|█████ | 10/20 [00:00<00:00, 11.29it/s][A
55%|█████▌ | 11/20 [00:01<00:00, 9.46it/s]
Total progress: 60%|██████ | 12/20 [00:01<00:00, 10.91it/s][A
65%|██████▌ | 13/20 [00:01<00:00, 9.73it/s]
Total progress: 70%|███████ | 14/20 [00:01<00:00, 10.72it/s][A
75%|███████▌ | 15/20 [00:01<00:00, 9.92it/s]
Total progress: 80%|████████ | 16/20 [00:01<00:00, 10.62it/s][A
85%|████████▌ | 17/20 [00:01<00:00, 10.11it/s]
Total progress: 90%|█████████ | 18/20 [00:01<00:00, 10.60it/s][A
95%|█████████▌| 19/20 [00:02<00:00, 10.17it/s]
Total progress: 100%|██████████| 20/20 [00:01<00:00, 10.48it/s][A
100%|██████████| 20/20 [00:02<00:00, 9.02it/s]
[Unload] Trying to free 1296.42 MB for cuda:0 with 0 models keep loaded ... Current free memory is 11685.12 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 11685.12 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 10501.56 MB, All loaded to GPU.
Moving model(s) has taken 0.10 seconds
Total progress: 100%|██████████| 20/20 [00:02<00:00, 10.48it/s][A
Total progress: 100%|██████████| 20/20 [00:02<00:00, 9.40it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 11514.11 MB ... Unload model JointTextEncoder Current free memory is 13274.47 MB ... Unload model KModel Current free memory is 18271.81 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "Euler" -> "Euler", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 18434.88 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 15657.90 MB, All loaded to GPU.
Moving model(s) has taken 0.80 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 16675.41 MB ... Done.
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 16674.79 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 16674.79 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 10753.74 MB, All loaded to GPU.
Moving model(s) has taken 1.82 seconds
0%| | 0/1 [00:00<?, ?it/s]
Total progress: 0%| | 0/1 [00:00<?, ?it/s][A
100%|██████████| 1/1 [00:00<00:00, 11.07it/s]
[Unload] Trying to free 1231.42 MB for cuda:0 with 0 models keep loaded ... Current free memory is 11674.41 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 11674.41 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 10490.85 MB, All loaded to GPU.
Moving model(s) has taken 0.10 seconds
Total progress: 100%|██████████| 1/1 [00:00<00:00, 7.12it/s][A
Total progress: 100%|██████████| 1/1 [00:00<00:00, 7.11it/s]
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 742.46 MB ... Unload model KModel Current free memory is 5742.85 MB ... Done.
Memory cleanup has taken 2.28 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 5742.24 MB ... Done.
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 5741.56 MB ... Unload model IntegratedAutoencoderKL Current free memory is 5902.38 MB ... Unload model JointTextEncoder Done.
[Memory Management] Target: KModel, Free GPU: 7661.24 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 1740.19 MB, All loaded to GPU.
Moving model(s) has taken 3.28 seconds
0%| | 0/20 [00:00<?, ?it/s]
Total progress: 0%| | 0/20 [00:00<?, ?it/s][A
10%|█ | 2/20 [00:00<00:01, 10.25it/s]
Total progress: 15%|█▌ | 3/20 [00:00<00:01, 16.22it/s][A
20%|██ | 4/20 [00:00<00:01, 9.46it/s]
Total progress: 25%|██▌ | 5/20 [00:00<00:01, 11.55it/s][A
25%|██▌ | 5/20 [00:00<00:01, 9.25it/s]
30%|███ | 6/20 [00:00<00:01, 8.79it/s]
Total progress: 35%|███▌ | 7/20 [00:00<00:01, 9.89it/s][A
35%|███▌ | 7/20 [00:00<00:01, 8.81it/s]
40%|████ | 8/20 [00:00<00:01, 8.81it/s]
Total progress: 45%|████▌ | 9/20 [00:00<00:01, 9.24it/s][A
45%|████▌ | 9/20 [00:01<00:01, 8.57it/s]
Total progress: 50%|█████ | 10/20 [00:01<00:01, 9.07it/s][A
50%|█████ | 10/20 [00:01<00:01, 8.48it/s]
Total progress: 55%|█████▌ | 11/20 [00:01<00:01, 8.94it/s][A
55%|█████▌ | 11/20 [00:01<00:01, 8.24it/s]
Total progress: 60%|██████ | 12/20 [00:01<00:00, 8.37it/s][A
60%|██████ | 12/20 [00:01<00:01, 7.99it/s]
Total progress: 65%|██████▌ | 13/20 [00:01<00:00, 8.39it/s][A
65%|██████▌ | 13/20 [00:01<00:00, 8.00it/s]
Total progress: 70%|███████ | 14/20 [00:01<00:00, 8.25it/s][A
70%|███████ | 14/20 [00:01<00:00, 8.20it/s]
Total progress: 75%|███████▌ | 15/20 [00:01<00:00, 8.47it/s][A
75%|███████▌ | 15/20 [00:01<00:00, 8.36it/s]
Total progress: 80%|████████ | 16/20 [00:01<00:00, 8.45it/s][A
80%|████████ | 16/20 [00:01<00:00, 8.30it/s]
Total progress: 85%|████████▌ | 17/20 [00:01<00:00, 8.33it/s][A
85%|████████▌ | 17/20 [00:01<00:00, 8.45it/s]
90%|█████████ | 18/20 [00:02<00:00, 8.60it/s]
Total progress: 95%|█████████▌| 19/20 [00:02<00:00, 8.61it/s][A
95%|█████████▌| 19/20 [00:02<00:00, 8.59it/s]
Total progress: 100%|██████████| 20/20 [00:02<00:00, 8.53it/s][A
100%|██████████| 20/20 [00:02<00:00, 8.61it/s]
100%|██████████| 20/20 [00:02<00:00, 8.59it/s]
[Unload] Trying to free 1296.42 MB for cuda:0 with 0 models keep loaded ... Current free memory is 2662.12 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 2662.12 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 1478.56 MB, All loaded to GPU.
Moving model(s) has taken 0.14 seconds
Total progress: 100%|██████████| 20/20 [00:02<00:00, 8.53it/s][A
Total progress: 100%|██████████| 20/20 [00:02<00:00, 7.81it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 2498.16 MB ... Unload model KModel Current free memory is 7497.16 MB ... Unload model IntegratedAutoencoderKL Done.
ERROR: Exception in ASGI application
Traceback (most recent call last):
File "/opt/sd-webui/venv/lib/python3.12/site-packages/uvicorn/protocols/http/h11_impl.py", line 410, in run_asgi
result = await app( # type: ignore[func-returns-value]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/sd-webui/venv/lib/python3.12/site-packages/uvicorn/middleware/proxy_headers.py", line 60, in __call__
return await self.app(scope, receive, send)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/sd-webui/venv/lib/python3.12/site-packages/fastapi/applications.py", line 1106, in __call__
await super().__call__(scope, receive, send)
File "/opt/sd-webui/venv/lib/python3.12/site-packages/starlette/applications.py", line 122, in __call__
await self.middleware_stack(scope, receive, send)
File "/opt/sd-webui/venv/lib/python3.12/site-packages/starlette/middleware/errors.py", line 184, in __call__
raise exc
File "/opt/sd-webui/venv/lib/python3.12/site-packages/starlette/middleware/errors.py", line 162, in __call__
await self.app(scope, receive, _send)
File "/opt/sd-webui/venv/lib/python3.12/site-packages/gradio/route_utils.py", line 724, in __call__
await self.app(scope, receive, send)
File "/opt/sd-webui/venv/lib/python3.12/site-packages/starlette/middleware/exceptions.py", line 79, in __call__
raise exc
File "/opt/sd-webui/venv/lib/python3.12/site-packages/starlette/middleware/exceptions.py", line 68, in __call__
await self.app(scope, receive, sender)
File "/opt/sd-webui/venv/lib/python3.12/site-packages/fastapi/middleware/asyncexitstack.py", line 20, in __call__
raise e
File "/opt/sd-webui/venv/lib/python3.12/site-packages/fastapi/middleware/asyncexitstack.py", line 17, in __call__
await self.app(scope, receive, send)
File "/opt/sd-webui/venv/lib/python3.12/site-packages/starlette/routing.py", line 718, in __call__
await route.handle(scope, receive, send)
File "/opt/sd-webui/venv/lib/python3.12/site-packages/starlette/routing.py", line 276, in handle
await self.app(scope, receive, send)
File "/opt/sd-webui/venv/lib/python3.12/site-packages/starlette/routing.py", line 66, in app
response = await func(request)
^^^^^^^^^^^^^^^^^^^
File "/opt/sd-webui/venv/lib/python3.12/site-packages/fastapi/routing.py", line 292, in app
content = await serialize_response(
^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/sd-webui/venv/lib/python3.12/site-packages/fastapi/routing.py", line 155, in serialize_response
raise ResponseValidationError(
fastapi.exceptions.ResponseValidationError: 1 validation errors:
{'type': 'string_type', 'loc': ('response', 'port'), 'msg': 'Input should be a valid string', 'input': 7887, 'url': 'https://errors.pydantic.dev/2.8/v/string_type'}
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 1231.42 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 18427.65 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 17244.09 MB, All loaded to GPU.
Moving model(s) has taken 0.10 seconds
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Current free memory is 18270.86 MB ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 18270.86 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 15493.88 MB, All loaded to GPU.
Moving model(s) has taken 0.64 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 16505.88 MB ... Done.
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 16505.82 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 16505.82 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 10584.77 MB, All loaded to GPU.
Moving model(s) has taken 1.87 seconds
0%| | 0/19 [00:00<?, ?it/s]
Total progress: 0%| | 0/19 [00:00<?, ?it/s][A
11%|█ | 2/19 [00:00<00:01, 13.44it/s]
Total progress: 16%|█▌ | 3/19 [00:00<00:00, 19.91it/s][A
21%|██ | 4/19 [00:00<00:01, 12.42it/s]
Total progress: 26%|██▋ | 5/19 [00:00<00:00, 14.57it/s][A
32%|███▏ | 6/19 [00:00<00:01, 11.71it/s]
Total progress: 37%|███▋ | 7/19 [00:00<00:00, 12.82it/s][A
42%|████▏ | 8/19 [00:00<00:00, 11.25it/s]
Total progress: 47%|████▋ | 9/19 [00:00<00:00, 11.88it/s][A
53%|█████▎ | 10/19 [00:00<00:00, 10.94it/s]
Total progress: 58%|█████▊ | 11/19 [00:00<00:00, 11.32it/s][A
63%|██████▎ | 12/19 [00:01<00:00, 10.61it/s]
Total progress: 68%|██████▊ | 13/19 [00:01<00:00, 10.82it/s][A
74%|███████▎ | 14/19 [00:01<00:00, 10.36it/s]
Total progress: 79%|███████▉ | 15/19 [00:01<00:00, 10.49it/s][A
84%|████████▍ | 16/19 [00:01<00:00, 10.19it/s]
Total progress: 89%|████████▉ | 17/19 [00:01<00:00, 10.28it/s][A
95%|█████████▍| 18/19 [00:01<00:00, 10.07it/s]
Total progress: 100%|██████████| 19/19 [00:01<00:00, 10.13it/s][A
100%|██████████| 19/19 [00:01<00:00, 10.61it/s]
[Unload] Trying to free 1089.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 11505.25 MB ... Done.
Total progress: 100%|██████████| 19/19 [00:01<00:00, 10.13it/s][A
Total progress: 100%|██████████| 19/19 [00:01<00:00, 10.04it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 11505.31 MB ... Unload model JointTextEncoder Current free memory is 13270.29 MB ... Unload model KModel Current free memory is 18270.68 MB ... Unload model IntegratedAutoencoderKL Done.
################################################################
[1m[32mInstall script for stable-diffusion + Web UI
[1m[34mTested on Debian 11 (Bullseye), Fedora 34+ and openSUSE Leap 15.4 or newer.[0m
################################################################
################################################################
Running on [1m[32mroot[0m user
################################################################
################################################################
Repo already cloned, using it as install directory
################################################################
################################################################
Create and activate python venv
################################################################
################################################################
Launching launch.py...
################################################################
glibc version is 2.39
Check TCMalloc: libtcmalloc_minimal.so.4
libtcmalloc_minimal.so.4 is linked with libc.so,execute LD_PRELOAD=/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4
=============================================================================================
INCOMPATIBLE PYTHON VERSION
This program is tested with 3.10.6 Python, but you have 3.12.3.
If you encounter an error with "RuntimeError: Couldn't install torch." message,
or any other error regarding unsuccessful package (library) installation,
please downgrade (or upgrade) to the latest version of 3.10 Python
and delete current Python and "venv" folder in WebUI's directory.
You can download 3.10 Python from here: https://www.python.org/downloads/release/python-3106/
Use --skip-python-version-check to suppress this warning.
=============================================================================================
Python 3.12.3 (main, Jan 22 2026, 20:57:42) [GCC 13.3.0]
Version: f2.0.1v1.10.1-previous-669-gdfdcbab6
Commit hash: dfdcbab685e57677014f05a3309b48cc87383167
Legacy Preprocessor init warning: Unable to install insightface automatically. Please try run `pip install insightface` manually.
Launching Web UI with arguments: -f --listen --api --enable-insecure-extension-access --xformers --no-half-vae --port 7887
Total VRAM 20017 MB, total RAM 64105 MB
pytorch version: 2.3.1+cu121
WARNING:xformers:A matching Triton is not available, some optimizations will not be enabled
Traceback (most recent call last):
File "/opt/sd-webui/venv/lib/python3.12/site-packages/xformers/__init__.py", line 57, in _is_triton_available
import triton # noqa
^^^^^^^^^^^^^
ModuleNotFoundError: No module named 'triton'
xformers version: 0.0.27
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA RTX 4000 SFF Ada Generation : native
Hint: your device supports --cuda-malloc for potential speed improvements.
VAE dtype preferences: [torch.bfloat16, torch.float32] -> torch.bfloat16
CUDA Using Stream: False
Using xformers cross attention
Using xformers attention for VAE
ControlNet preprocessor location: /opt/sd-webui/models/ControlNetPreprocessor
*** Error loading script: soft_inpainting.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 525, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/sd-webui/modules/script_loading.py", line 13, in load_module
module_spec.loader.exec_module(module)
File "<frozen importlib._bootstrap_external>", line 995, in exec_module
File "<frozen importlib._bootstrap>", line 488, in _call_with_frames_removed
File "/opt/sd-webui/extensions-builtin/soft-inpainting/scripts/soft_inpainting.py", line 10, in <module>
from joblib import Parallel, delayed, cpu_count
ModuleNotFoundError: No module named 'joblib'
---
2026-02-11 15:37:58,882 - ControlNet - [0;32mINFO[0m - ControlNet UI callback registered.
Model selected: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
Using online LoRAs in FP16: False
Running on local URL: http://0.0.0.0:7887
To create a public link, set `share=True` in `launch()`.
Startup time: 29.3s (prepare environment: 7.2s, launcher: 1.9s, import torch: 14.5s, other imports: 0.4s, load scripts: 1.9s, create ui: 1.8s, gradio launch: 0.6s, add APIs: 0.9s).
################################################################
[1m[32mInstall script for stable-diffusion + Web UI
[1m[34mTested on Debian 11 (Bullseye), Fedora 34+ and openSUSE Leap 15.4 or newer.[0m
################################################################
################################################################
Running on [1m[32mroot[0m user
################################################################
################################################################
Repo already cloned, using it as install directory
################################################################
################################################################
[1m[32mInstall script for stable-diffusion + Web UI
[1m[34mTested on Debian 11 (Bullseye), Fedora 34+ and openSUSE Leap 15.4 or newer.[0m
################################################################
################################################################
Running on [1m[32mroot[0m user
################################################################
################################################################
Repo already cloned, using it as install directory
################################################################
################################################################
Create and activate python venv
################################################################
################################################################
Launching launch.py...
################################################################
glibc version is 2.39
Check TCMalloc: libtcmalloc_minimal.so.4
libtcmalloc_minimal.so.4 is linked with libc.so,execute LD_PRELOAD=/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4
=============================================================================================
INCOMPATIBLE PYTHON VERSION
This program is tested with 3.10.6 Python, but you have 3.12.3.
If you encounter an error with "RuntimeError: Couldn't install torch." message,
or any other error regarding unsuccessful package (library) installation,
please downgrade (or upgrade) to the latest version of 3.10 Python
and delete current Python and "venv" folder in WebUI's directory.
You can download 3.10 Python from here: https://www.python.org/downloads/release/python-3106/
Use --skip-python-version-check to suppress this warning.
=============================================================================================
Python 3.12.3 (main, Jan 22 2026, 20:57:42) [GCC 13.3.0]
Version: f2.0.1v1.10.1-previous-669-gdfdcbab6
Commit hash: dfdcbab685e57677014f05a3309b48cc87383167
Legacy Preprocessor init warning: Unable to install insightface automatically. Please try run `pip install insightface` manually.
Launching Web UI with arguments: -f --listen --api --enable-insecure-extension-access --xformers --no-half-vae --port 7887
Total VRAM 20017 MB, total RAM 64105 MB
pytorch version: 2.3.1+cu121
WARNING:xformers:A matching Triton is not available, some optimizations will not be enabled
Traceback (most recent call last):
File "/opt/sd-webui/venv/lib/python3.12/site-packages/xformers/__init__.py", line 57, in _is_triton_available
import triton # noqa
^^^^^^^^^^^^^
ModuleNotFoundError: No module named 'triton'
xformers version: 0.0.27
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA RTX 4000 SFF Ada Generation : native
Hint: your device supports --cuda-malloc for potential speed improvements.
VAE dtype preferences: [torch.bfloat16, torch.float32] -> torch.bfloat16
CUDA Using Stream: False
Using xformers cross attention
Using xformers attention for VAE
ControlNet preprocessor location: /opt/sd-webui/models/ControlNetPreprocessor
*** Error loading script: soft_inpainting.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 525, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/sd-webui/modules/script_loading.py", line 13, in load_module
module_spec.loader.exec_module(module)
File "<frozen importlib._bootstrap_external>", line 995, in exec_module
File "<frozen importlib._bootstrap>", line 488, in _call_with_frames_removed
File "/opt/sd-webui/extensions-builtin/soft-inpainting/scripts/soft_inpainting.py", line 10, in <module>
from joblib import Parallel, delayed, cpu_count
ModuleNotFoundError: No module named 'joblib'
---
2026-02-12 06:37:59,335 - ControlNet - [0;32mINFO[0m - ControlNet UI callback registered.
Model selected: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
Using online LoRAs in FP16: False
Running on local URL: http://0.0.0.0:7887
To create a public link, set `share=True` in `launch()`.
Startup time: 9.6s (prepare environment: 1.8s, launcher: 0.2s, import torch: 3.9s, other imports: 0.2s, load scripts: 0.9s, create ui: 1.2s, gradio launch: 0.6s, add APIs: 0.7s).
################################################################
[1m[32mInstall script for stable-diffusion + Web UI
[1m[34mTested on Debian 11 (Bullseye), Fedora 34+ and openSUSE Leap 15.4 or newer.[0m
################################################################
################################################################
Running on [1m[32mroot[0m user
################################################################
################################################################
Repo already cloned, using it as install directory
################################################################
################################################################
Create and activate python venv
################################################################
################################################################
Launching launch.py...
################################################################
glibc version is 2.39
Check TCMalloc: libtcmalloc_minimal.so.4
libtcmalloc_minimal.so.4 is linked with libc.so,execute LD_PRELOAD=/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4
=============================================================================================
INCOMPATIBLE PYTHON VERSION
This program is tested with 3.10.6 Python, but you have 3.12.3.
If you encounter an error with "RuntimeError: Couldn't install torch." message,
or any other error regarding unsuccessful package (library) installation,
please downgrade (or upgrade) to the latest version of 3.10 Python
and delete current Python and "venv" folder in WebUI's directory.
You can download 3.10 Python from here: https://www.python.org/downloads/release/python-3106/
Use --skip-python-version-check to suppress this warning.
=============================================================================================
Python 3.12.3 (main, Jan 22 2026, 20:57:42) [GCC 13.3.0]
Version: f2.0.1v1.10.1-previous-669-gdfdcbab6
Commit hash: dfdcbab685e57677014f05a3309b48cc87383167
Legacy Preprocessor init warning: Unable to install insightface automatically. Please try run `pip install insightface` manually.
Launching Web UI with arguments: -f --listen --api --enable-insecure-extension-access --xformers --no-half-vae --port 7887
Total VRAM 20017 MB, total RAM 64105 MB
pytorch version: 2.3.1+cu121
WARNING:xformers:A matching Triton is not available, some optimizations will not be enabled
Traceback (most recent call last):
File "/opt/sd-webui/venv/lib/python3.12/site-packages/xformers/__init__.py", line 57, in _is_triton_available
import triton # noqa
^^^^^^^^^^^^^
ModuleNotFoundError: No module named 'triton'
xformers version: 0.0.27
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA RTX 4000 SFF Ada Generation : native
Hint: your device supports --cuda-malloc for potential speed improvements.
VAE dtype preferences: [torch.bfloat16, torch.float32] -> torch.bfloat16
CUDA Using Stream: False
Using xformers cross attention
Using xformers attention for VAE
ControlNet preprocessor location: /opt/sd-webui/models/ControlNetPreprocessor
*** Error loading script: soft_inpainting.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 525, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/sd-webui/modules/script_loading.py", line 13, in load_module
module_spec.loader.exec_module(module)
File "<frozen importlib._bootstrap_external>", line 995, in exec_module
File "<frozen importlib._bootstrap>", line 488, in _call_with_frames_removed
File "/opt/sd-webui/extensions-builtin/soft-inpainting/scripts/soft_inpainting.py", line 10, in <module>
from joblib import Parallel, delayed, cpu_count
ModuleNotFoundError: No module named 'joblib'
---
2026-02-12 06:38:33,582 - ControlNet - [0;32mINFO[0m - ControlNet UI callback registered.
Model selected: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
Using online LoRAs in FP16: False
Running on local URL: http://0.0.0.0:7887
To create a public link, set `share=True` in `launch()`.
################################################################
[1m[32mInstall script for stable-diffusion + Web UI
[1m[34mTested on Debian 11 (Bullseye), Fedora 34+ and openSUSE Leap 15.4 or newer.[0m
################################################################
################################################################
Running on [1m[32mroot[0m user
################################################################
################################################################
Repo already cloned, using it as install directory
################################################################
################################################################
Create and activate python venv
################################################################
################################################################
Launching launch.py...
################################################################
glibc version is 2.39
Check TCMalloc: libtcmalloc_minimal.so.4
libtcmalloc_minimal.so.4 is linked with libc.so,execute LD_PRELOAD=/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4
=============================================================================================
INCOMPATIBLE PYTHON VERSION
This program is tested with 3.10.6 Python, but you have 3.12.3.
If you encounter an error with "RuntimeError: Couldn't install torch." message,
or any other error regarding unsuccessful package (library) installation,
please downgrade (or upgrade) to the latest version of 3.10 Python
and delete current Python and "venv" folder in WebUI's directory.
You can download 3.10 Python from here: https://www.python.org/downloads/release/python-3106/
Use --skip-python-version-check to suppress this warning.
=============================================================================================
Python 3.12.3 (main, Jan 22 2026, 20:57:42) [GCC 13.3.0]
Version: f2.0.1v1.10.1-previous-669-gdfdcbab6
Commit hash: dfdcbab685e57677014f05a3309b48cc87383167
Legacy Preprocessor init warning: Unable to install insightface automatically. Please try run `pip install insightface` manually.
Launching Web UI with arguments: -f --listen --api --enable-insecure-extension-access --xformers --no-half-vae --port 7887
Total VRAM 20017 MB, total RAM 64105 MB
pytorch version: 2.3.1+cu121
WARNING:xformers:A matching Triton is not available, some optimizations will not be enabled
Traceback (most recent call last):
File "/opt/sd-webui/venv/lib/python3.12/site-packages/xformers/__init__.py", line 57, in _is_triton_available
import triton # noqa
^^^^^^^^^^^^^
ModuleNotFoundError: No module named 'triton'
xformers version: 0.0.27
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA RTX 4000 SFF Ada Generation : native
Hint: your device supports --cuda-malloc for potential speed improvements.
VAE dtype preferences: [torch.bfloat16, torch.float32] -> torch.bfloat16
CUDA Using Stream: False
Using xformers cross attention
Using xformers attention for VAE
ControlNet preprocessor location: /opt/sd-webui/models/ControlNetPreprocessor
*** Error loading script: soft_inpainting.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 525, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/sd-webui/modules/script_loading.py", line 13, in load_module
module_spec.loader.exec_module(module)
File "<frozen importlib._bootstrap_external>", line 995, in exec_module
File "<frozen importlib._bootstrap>", line 488, in _call_with_frames_removed
File "/opt/sd-webui/extensions-builtin/soft-inpainting/scripts/soft_inpainting.py", line 10, in <module>
from joblib import Parallel, delayed, cpu_count
ModuleNotFoundError: No module named 'joblib'
---
2026-02-12 06:57:32,734 - ControlNet - [0;32mINFO[0m - ControlNet UI callback registered.
Model selected: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
Using online LoRAs in FP16: False
Running on local URL: http://0.0.0.0:7887
To create a public link, set `share=True` in `launch()`.
Loading Model: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Done.
Startup time: 7.4s (prepare environment: 1.1s, launcher: 0.2s, import torch: 2.9s, load scripts: 0.7s, create ui: 1.0s, gradio launch: 0.5s, add APIs: 0.8s).
StateDict Keys: {'unet': 1680, 'vae': 248, 'text_encoder': 197, 'text_encoder_2': 518, 'ignore': 0}
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
K-Model Created: {'storage_dtype': torch.float16, 'computation_dtype': torch.float16}
Model loaded in 1.1s (unload existing model: 0.1s, forge model load: 1.0s).
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3051.58 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 10342.15 MB, Model Require: 1559.68 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 7758.47 MB, All loaded to GPU.
Moving model(s) has taken 1.15 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 8538.44 MB ... Done.
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 8537.77 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 8537.77 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 2616.72 MB, All loaded to GPU.
Moving model(s) has taken 4.43 seconds
0%| | 0/20 [00:00<?, ?it/s]
Total progress: 0%| | 0/20 [00:00<?, ?it/s][A
5%|▌ | 1/20 [00:00<00:09, 1.96it/s]
Total progress: 15%|█▌ | 3/20 [00:00<00:00, 21.08it/s][A
15%|█▌ | 3/20 [00:00<00:03, 4.99it/s]
25%|██▌ | 5/20 [00:00<00:02, 7.03it/s]
Total progress: 30%|███ | 6/20 [00:00<00:01, 13.99it/s][A
35%|███▌ | 7/20 [00:01<00:01, 8.24it/s]
Total progress: 40%|████ | 8/20 [00:00<00:00, 12.59it/s][A
45%|████▌ | 9/20 [00:01<00:01, 8.97it/s]
Total progress: 50%|█████ | 10/20 [00:00<00:00, 11.78it/s][A
55%|█████▌ | 11/20 [00:01<00:00, 9.41it/s]
Total progress: 60%|██████ | 12/20 [00:00<00:00, 11.24it/s][A
65%|██████▌ | 13/20 [00:01<00:00, 9.67it/s]
Total progress: 70%|███████ | 14/20 [00:01<00:00, 10.92it/s][A
75%|███████▌ | 15/20 [00:01<00:00, 9.90it/s]
Total progress: 80%|████████ | 16/20 [00:01<00:00, 10.76it/s][A
85%|████████▌ | 17/20 [00:02<00:00, 10.05it/s]
Total progress: 90%|█████████ | 18/20 [00:01<00:00, 10.65it/s][A
95%|█████████▌| 19/20 [00:02<00:00, 10.13it/s]
Total progress: 100%|██████████| 20/20 [00:01<00:00, 10.53it/s][A
100%|██████████| 20/20 [00:02<00:00, 8.66it/s]
[Unload] Trying to free 1296.42 MB for cuda:0 with 0 models keep loaded ... Current free memory is 3522.31 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 3522.31 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 2338.75 MB, All loaded to GPU.
Moving model(s) has taken 0.10 seconds
Total progress: 100%|██████████| 20/20 [00:02<00:00, 10.53it/s][A
Total progress: 100%|██████████| 20/20 [00:02<00:00, 9.59it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 3351.30 MB ... Unload model JointTextEncoder Current free memory is 5111.66 MB ... Unload model KModel Current free memory is 10108.99 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[LORA] Loaded /opt/sd-webui/models/Lora/Octi_20260206_230414.safetensors for KModel-UNet with 722 keys at weight 0.8 (skipped 0 keys) with on_the_fly = False
[LORA] Loaded /opt/sd-webui/models/Lora/Octi_20260206_230414.safetensors for KModel-CLIP with 264 keys at weight 0.8 (skipped 0 keys) with on_the_fly = False
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 10273.35 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 7496.37 MB, All loaded to GPU.
Moving model(s) has taken 1.96 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 8515.76 MB ... Done.
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 8515.08 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 8515.08 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 2594.03 MB, All loaded to GPU.
Moving model(s) has taken 5.51 seconds
0%| | 0/20 [00:00<?, ?it/s]
Total progress: 0%| | 0/20 [00:00<?, ?it/s][A
10%|█ | 2/20 [00:00<00:01, 13.25it/s]
Total progress: 15%|█▌ | 3/20 [00:00<00:00, 20.34it/s][A
20%|██ | 4/20 [00:00<00:01, 12.46it/s]
Total progress: 30%|███ | 6/20 [00:00<00:01, 13.67it/s][A
30%|███ | 6/20 [00:00<00:01, 11.56it/s]
Total progress: 40%|████ | 8/20 [00:00<00:00, 12.40it/s][A
40%|████ | 8/20 [00:00<00:01, 11.19it/s]
Total progress: 50%|█████ | 10/20 [00:00<00:00, 11.72it/s][A
50%|█████ | 10/20 [00:00<00:00, 10.89it/s]
Total progress: 60%|██████ | 12/20 [00:00<00:00, 11.04it/s][A
60%|██████ | 12/20 [00:01<00:00, 10.51it/s]
Total progress: 70%|███████ | 14/20 [00:01<00:00, 10.65it/s][A
70%|███████ | 14/20 [00:01<00:00, 10.31it/s]
Total progress: 80%|████████ | 16/20 [00:01<00:00, 10.48it/s][A
80%|████████ | 16/20 [00:01<00:00, 10.26it/s]
Total progress: 90%|█████████ | 18/20 [00:01<00:00, 10.35it/s][A
90%|█████████ | 18/20 [00:01<00:00, 10.20it/s]
Total progress: 100%|██████████| 20/20 [00:01<00:00, 10.30it/s][A
100%|██████████| 20/20 [00:01<00:00, 10.19it/s]
100%|██████████| 20/20 [00:01<00:00, 10.62it/s]
[Unload] Trying to free 1296.42 MB for cuda:0 with 0 models keep loaded ... Current free memory is 3541.28 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 3541.28 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 2357.72 MB, All loaded to GPU.
Moving model(s) has taken 0.10 seconds
Total progress: 100%|██████████| 20/20 [00:02<00:00, 10.30it/s][A
Total progress: 100%|██████████| 20/20 [00:02<00:00, 9.68it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 3378.78 MB ... Unload model JointTextEncoder Current free memory is 5135.76 MB ... Unload model KModel Current free memory is 10109.43 MB ... Unload model IntegratedAutoencoderKL Done.
################################################################
[1m[32mInstall script for stable-diffusion + Web UI
[1m[34mTested on Debian 11 (Bullseye), Fedora 34+ and openSUSE Leap 15.4 or newer.[0m
################################################################
################################################################
Running on [1m[32mroot[0m user
################################################################
################################################################
Repo already cloned, using it as install directory
################################################################
################################################################
Create and activate python venv
################################################################
################################################################
Launching launch.py...
################################################################
glibc version is 2.39
Check TCMalloc: libtcmalloc_minimal.so.4
libtcmalloc_minimal.so.4 is linked with libc.so,execute LD_PRELOAD=/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4
=============================================================================================
INCOMPATIBLE PYTHON VERSION
This program is tested with 3.10.6 Python, but you have 3.12.3.
If you encounter an error with "RuntimeError: Couldn't install torch." message,
or any other error regarding unsuccessful package (library) installation,
please downgrade (or upgrade) to the latest version of 3.10 Python
and delete current Python and "venv" folder in WebUI's directory.
You can download 3.10 Python from here: https://www.python.org/downloads/release/python-3106/
Use --skip-python-version-check to suppress this warning.
=============================================================================================
Python 3.12.3 (main, Jan 22 2026, 20:57:42) [GCC 13.3.0]
Version: f2.0.1v1.10.1-previous-669-gdfdcbab6
Commit hash: dfdcbab685e57677014f05a3309b48cc87383167
Legacy Preprocessor init warning: Unable to install insightface automatically. Please try run `pip install insightface` manually.
Launching Web UI with arguments: -f --listen --api --enable-insecure-extension-access --xformers --no-half-vae --port 7887
Total VRAM 20017 MB, total RAM 64105 MB
pytorch version: 2.3.1+cu121
WARNING:xformers:A matching Triton is not available, some optimizations will not be enabled
Traceback (most recent call last):
File "/opt/sd-webui/venv/lib/python3.12/site-packages/xformers/__init__.py", line 57, in _is_triton_available
import triton # noqa
^^^^^^^^^^^^^
ModuleNotFoundError: No module named 'triton'
xformers version: 0.0.27
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA RTX 4000 SFF Ada Generation : native
Hint: your device supports --cuda-malloc for potential speed improvements.
VAE dtype preferences: [torch.bfloat16, torch.float32] -> torch.bfloat16
CUDA Using Stream: False
Using xformers cross attention
Using xformers attention for VAE
ControlNet preprocessor location: /opt/sd-webui/models/ControlNetPreprocessor
*** Error loading script: soft_inpainting.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 525, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/sd-webui/modules/script_loading.py", line 13, in load_module
module_spec.loader.exec_module(module)
File "<frozen importlib._bootstrap_external>", line 995, in exec_module
File "<frozen importlib._bootstrap>", line 488, in _call_with_frames_removed
File "/opt/sd-webui/extensions-builtin/soft-inpainting/scripts/soft_inpainting.py", line 10, in <module>
from joblib import Parallel, delayed, cpu_count
ModuleNotFoundError: No module named 'joblib'
---
2026-02-12 07:02:43,612 - ControlNet - [0;32mINFO[0m - ControlNet UI callback registered.
Model selected: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
Using online LoRAs in FP16: False
Running on local URL: http://0.0.0.0:7887
To create a public link, set `share=True` in `launch()`.
Startup time: 9.4s (prepare environment: 1.4s, launcher: 0.3s, import torch: 3.9s, other imports: 0.1s, load scripts: 1.2s, create ui: 1.2s, gradio launch: 0.5s, add APIs: 0.8s).
Model selected: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/ponyRealism_V22.safetensors', 'hash': 'd84eb26b'}, 'additional_modules': [], 'unet_storage_dtype': None}
Using online LoRAs in FP16: False
Loading Model: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/ponyRealism_V22.safetensors', 'hash': 'd84eb26b'}, 'additional_modules': [], 'unet_storage_dtype': None}
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Done.
StateDict Keys: {'unet': 1680, 'vae': 248, 'text_encoder': 197, 'text_encoder_2': 518, 'ignore': 0}
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
K-Model Created: {'storage_dtype': torch.float16, 'computation_dtype': torch.float16}
Model loaded in 1.2s (unload existing model: 0.1s, forge model load: 1.0s).
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[LORA] Loaded /opt/sd-webui/models/Lora/Octi_20260206_230414.safetensors for KModel-UNet with 722 keys at weight 0.8 (skipped 0 keys) with on_the_fly = False
[LORA] Loaded /opt/sd-webui/models/Lora/Octi_20260206_230414.safetensors for KModel-CLIP with 264 keys at weight 0.8 (skipped 0 keys) with on_the_fly = False
[Unload] Trying to free 3051.58 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 10342.15 MB, Model Require: 1559.68 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 7758.47 MB, All loaded to GPU.
Moving model(s) has taken 2.34 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 8538.94 MB ... Done.
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 8538.27 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 8538.27 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 2617.22 MB, All loaded to GPU.
Moving model(s) has taken 8.05 seconds
0%| | 0/12 [00:00<?, ?it/s]
Total progress: 0%| | 0/12 [00:00<?, ?it/s][A
8%|▊ | 1/12 [00:00<00:02, 3.74it/s]
Total progress: 25%|██▌ | 3/12 [00:00<00:00, 25.03it/s][A
25%|██▌ | 3/12 [00:00<00:01, 7.86it/s]
42%|████▏ | 5/12 [00:00<00:00, 9.97it/s]
Total progress: 50%|█████ | 6/12 [00:00<00:00, 15.99it/s][A
58%|█████▊ | 7/12 [00:00<00:00, 10.26it/s]
Total progress: 67%|██████▋ | 8/12 [00:00<00:00, 13.59it/s][A
75%|███████▌ | 9/12 [00:00<00:00, 10.52it/s]
Total progress: 83%|████████▎ | 10/12 [00:00<00:00, 12.60it/s][A
92%|█████████▏| 11/12 [00:01<00:00, 10.56it/s]
Total progress: 100%|██████████| 12/12 [00:00<00:00, 11.79it/s][A
100%|██████████| 12/12 [00:01<00:00, 9.75it/s]
[Unload] Trying to free 1296.42 MB for cuda:0 with 0 models keep loaded ... Current free memory is 3540.43 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 3540.43 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 2356.87 MB, All loaded to GPU.
Moving model(s) has taken 0.10 seconds
Model selected: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
Using online LoRAs in FP16: False
Total progress: 100%|██████████| 12/12 [00:01<00:00, 11.79it/s][A
Total progress: 100%|██████████| 12/12 [00:01<00:00, 9.68it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 3369.30 MB ... Unload model JointTextEncoder Current free memory is 5129.16 MB ... Unload model KModel Current free memory is 10108.87 MB ... Unload model IntegratedAutoencoderKL Done.
################################################################
[1m[32mInstall script for stable-diffusion + Web UI
[1m[34mTested on Debian 11 (Bullseye), Fedora 34+ and openSUSE Leap 15.4 or newer.[0m
################################################################
################################################################
Running on [1m[32mroot[0m user
################################################################
################################################################
Repo already cloned, using it as install directory
################################################################
################################################################
Create and activate python venv
################################################################
################################################################
Launching launch.py...
################################################################
glibc version is 2.39
Check TCMalloc: libtcmalloc_minimal.so.4
libtcmalloc_minimal.so.4 is linked with libc.so,execute LD_PRELOAD=/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4
=============================================================================================
INCOMPATIBLE PYTHON VERSION
This program is tested with 3.10.6 Python, but you have 3.12.3.
If you encounter an error with "RuntimeError: Couldn't install torch." message,
or any other error regarding unsuccessful package (library) installation,
please downgrade (or upgrade) to the latest version of 3.10 Python
and delete current Python and "venv" folder in WebUI's directory.
You can download 3.10 Python from here: https://www.python.org/downloads/release/python-3106/
Use --skip-python-version-check to suppress this warning.
=============================================================================================
Python 3.12.3 (main, Jan 22 2026, 20:57:42) [GCC 13.3.0]
Version: f2.0.1v1.10.1-previous-669-gdfdcbab6
Commit hash: dfdcbab685e57677014f05a3309b48cc87383167
Legacy Preprocessor init warning: Unable to install insightface automatically. Please try run `pip install insightface` manually.
Launching Web UI with arguments: -f --listen --api --enable-insecure-extension-access --xformers --no-half-vae --port 7887
Total VRAM 20017 MB, total RAM 64105 MB
pytorch version: 2.3.1+cu121
WARNING:xformers:A matching Triton is not available, some optimizations will not be enabled
Traceback (most recent call last):
File "/opt/sd-webui/venv/lib/python3.12/site-packages/xformers/__init__.py", line 57, in _is_triton_available
import triton # noqa
^^^^^^^^^^^^^
ModuleNotFoundError: No module named 'triton'
xformers version: 0.0.27
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA RTX 4000 SFF Ada Generation : native
Hint: your device supports --cuda-malloc for potential speed improvements.
VAE dtype preferences: [torch.bfloat16, torch.float32] -> torch.bfloat16
CUDA Using Stream: False
Using xformers cross attention
Using xformers attention for VAE
ControlNet preprocessor location: /opt/sd-webui/models/ControlNetPreprocessor
*** Error loading script: soft_inpainting.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 525, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/sd-webui/modules/script_loading.py", line 13, in load_module
module_spec.loader.exec_module(module)
File "<frozen importlib._bootstrap_external>", line 995, in exec_module
File "<frozen importlib._bootstrap>", line 488, in _call_with_frames_removed
File "/opt/sd-webui/extensions-builtin/soft-inpainting/scripts/soft_inpainting.py", line 10, in <module>
from joblib import Parallel, delayed, cpu_count
ModuleNotFoundError: No module named 'joblib'
---
2026-02-12 07:16:14,869 - ControlNet - [0;32mINFO[0m - ControlNet UI callback registered.
Model selected: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
Using online LoRAs in FP16: False
Running on local URL: http://0.0.0.0:7887
To create a public link, set `share=True` in `launch()`.
Startup time: 7.6s (prepare environment: 1.2s, launcher: 0.2s, import torch: 3.1s, other imports: 0.1s, load scripts: 0.7s, create ui: 1.1s, gradio launch: 0.5s, add APIs: 0.7s).
Model selected: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/ponyRealism_V22.safetensors', 'hash': 'd84eb26b'}, 'additional_modules': [], 'unet_storage_dtype': None}
Using online LoRAs in FP16: False
Loading Model: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/ponyRealism_V22.safetensors', 'hash': 'd84eb26b'}, 'additional_modules': [], 'unet_storage_dtype': None}
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Done.
StateDict Keys: {'unet': 1680, 'vae': 248, 'text_encoder': 197, 'text_encoder_2': 518, 'ignore': 0}
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
K-Model Created: {'storage_dtype': torch.float16, 'computation_dtype': torch.float16}
Model loaded in 0.5s (unload existing model: 0.1s, forge model load: 0.4s).
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[LORA] Loaded /opt/sd-webui/models/Lora/Octi_20260206_230414.safetensors for KModel-UNet with 722 keys at weight 0.8 (skipped 0 keys) with on_the_fly = False
[LORA] Loaded /opt/sd-webui/models/Lora/Octi_20260206_230414.safetensors for KModel-CLIP with 264 keys at weight 0.8 (skipped 0 keys) with on_the_fly = False
[Unload] Trying to free 3051.58 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 10342.15 MB, Model Require: 1559.68 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 7758.47 MB, All loaded to GPU.
Moving model(s) has taken 2.03 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 8538.94 MB ... Done.
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 8538.27 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 8538.27 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 2617.22 MB, All loaded to GPU.
Moving model(s) has taken 6.53 seconds
0%| | 0/20 [00:00<?, ?it/s]
Total progress: 0%| | 0/20 [00:00<?, ?it/s][A
5%|▌ | 1/20 [00:00<00:04, 3.93it/s]
Total progress: 15%|█▌ | 3/20 [00:00<00:00, 25.59it/s][A
15%|█▌ | 3/20 [00:00<00:02, 8.18it/s]
25%|██▌ | 5/20 [00:00<00:01, 9.71it/s]
Total progress: 30%|███ | 6/20 [00:00<00:00, 15.29it/s][A
35%|███▌ | 7/20 [00:00<00:01, 10.13it/s]
Total progress: 40%|████ | 8/20 [00:00<00:00, 13.26it/s][A
45%|████▌ | 9/20 [00:00<00:01, 10.33it/s]
Total progress: 50%|█████ | 10/20 [00:00<00:00, 12.23it/s][A
55%|█████▌ | 11/20 [00:01<00:00, 10.35it/s]
Total progress: 60%|██████ | 12/20 [00:00<00:00, 11.57it/s][A
65%|██████▌ | 13/20 [00:01<00:00, 10.45it/s]
Total progress: 70%|███████ | 14/20 [00:01<00:00, 11.28it/s][A
75%|███████▌ | 15/20 [00:01<00:00, 10.52it/s]
Total progress: 80%|████████ | 16/20 [00:01<00:00, 11.07it/s][A
85%|████████▌ | 17/20 [00:01<00:00, 10.41it/s]
Total progress: 90%|█████████ | 18/20 [00:01<00:00, 10.73it/s][A
95%|█████████▌| 19/20 [00:01<00:00, 10.27it/s]
Total progress: 100%|██████████| 20/20 [00:01<00:00, 10.40it/s][A
100%|██████████| 20/20 [00:02<00:00, 9.93it/s]
[Unload] Trying to free 1296.42 MB for cuda:0 with 0 models keep loaded ... Current free memory is 3540.43 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 3540.43 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 2356.87 MB, All loaded to GPU.
Moving model(s) has taken 0.10 seconds
Model selected: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
Using online LoRAs in FP16: False
Total progress: 100%|██████████| 20/20 [00:02<00:00, 10.40it/s][A
Total progress: 100%|██████████| 20/20 [00:02<00:00, 9.80it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 3369.30 MB ... Unload model JointTextEncoder Current free memory is 5129.16 MB ... Unload model KModel Current free memory is 10108.87 MB ... Unload model IntegratedAutoencoderKL Done.
################################################################
[1m[32mInstall script for stable-diffusion + Web UI
[1m[34mTested on Debian 11 (Bullseye), Fedora 34+ and openSUSE Leap 15.4 or newer.[0m
################################################################
################################################################
Running on [1m[32mroot[0m user
################################################################
################################################################
Repo already cloned, using it as install directory
################################################################
################################################################
Create and activate python venv
################################################################
################################################################
Launching launch.py...
################################################################
glibc version is 2.39
Check TCMalloc: libtcmalloc_minimal.so.4
libtcmalloc_minimal.so.4 is linked with libc.so,execute LD_PRELOAD=/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4
=============================================================================================
INCOMPATIBLE PYTHON VERSION
This program is tested with 3.10.6 Python, but you have 3.12.3.
If you encounter an error with "RuntimeError: Couldn't install torch." message,
or any other error regarding unsuccessful package (library) installation,
please downgrade (or upgrade) to the latest version of 3.10 Python
and delete current Python and "venv" folder in WebUI's directory.
You can download 3.10 Python from here: https://www.python.org/downloads/release/python-3106/
Use --skip-python-version-check to suppress this warning.
=============================================================================================
Python 3.12.3 (main, Jan 22 2026, 20:57:42) [GCC 13.3.0]
Version: f2.0.1v1.10.1-previous-669-gdfdcbab6
Commit hash: dfdcbab685e57677014f05a3309b48cc87383167
Legacy Preprocessor init warning: Unable to install insightface automatically. Please try run `pip install insightface` manually.
Launching Web UI with arguments: -f --listen --api --enable-insecure-extension-access --xformers --no-half-vae --port 7887
Total VRAM 20017 MB, total RAM 64105 MB
pytorch version: 2.3.1+cu121
WARNING:xformers:A matching Triton is not available, some optimizations will not be enabled
Traceback (most recent call last):
File "/opt/sd-webui/venv/lib/python3.12/site-packages/xformers/__init__.py", line 57, in _is_triton_available
import triton # noqa
^^^^^^^^^^^^^
ModuleNotFoundError: No module named 'triton'
xformers version: 0.0.27
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA RTX 4000 SFF Ada Generation : native
Hint: your device supports --cuda-malloc for potential speed improvements.
VAE dtype preferences: [torch.bfloat16, torch.float32] -> torch.bfloat16
CUDA Using Stream: False
Using xformers cross attention
Using xformers attention for VAE
ControlNet preprocessor location: /opt/sd-webui/models/ControlNetPreprocessor
*** Error loading script: soft_inpainting.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 525, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/sd-webui/modules/script_loading.py", line 13, in load_module
module_spec.loader.exec_module(module)
File "<frozen importlib._bootstrap_external>", line 995, in exec_module
File "<frozen importlib._bootstrap>", line 488, in _call_with_frames_removed
File "/opt/sd-webui/extensions-builtin/soft-inpainting/scripts/soft_inpainting.py", line 10, in <module>
from joblib import Parallel, delayed, cpu_count
ModuleNotFoundError: No module named 'joblib'
---
2026-02-12 07:19:06,322 - ControlNet - [0;32mINFO[0m - ControlNet UI callback registered.
Model selected: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
Using online LoRAs in FP16: False
Running on local URL: http://0.0.0.0:7887
To create a public link, set `share=True` in `launch()`.
Startup time: 8.3s (prepare environment: 1.3s, launcher: 0.2s, import torch: 3.6s, other imports: 0.1s, load scripts: 0.8s, create ui: 1.1s, gradio launch: 0.5s, add APIs: 0.7s).
Loading Model: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Done.
StateDict Keys: {'unet': 1680, 'vae': 248, 'text_encoder': 197, 'text_encoder_2': 518, 'ignore': 0}
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
K-Model Created: {'storage_dtype': torch.float16, 'computation_dtype': torch.float16}
Model loaded in 1.1s (unload existing model: 0.2s, forge model load: 0.9s).
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 1231.42 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 10312.25 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 9128.69 MB, All loaded to GPU.
Moving model(s) has taken 0.06 seconds
[Unload] Trying to free 3051.58 MB for cuda:0 with 0 models keep loaded ... Current free memory is 10137.36 MB ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 10137.36 MB, Model Require: 1559.68 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 7553.68 MB, All loaded to GPU.
Moving model(s) has taken 0.96 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 8352.66 MB ... Done.
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 8351.98 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 8351.98 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 2430.93 MB, All loaded to GPU.
Moving model(s) has taken 3.38 seconds
0%| | 0/19 [00:00<?, ?it/s]
Total progress: 0%| | 0/19 [00:00<?, ?it/s][A
5%|▌ | 1/19 [00:00<00:02, 6.49it/s]
Total progress: 16%|█▌ | 3/19 [00:00<00:00, 26.38it/s][A
16%|█▌ | 3/19 [00:00<00:01, 10.31it/s]
26%|██▋ | 5/19 [00:00<00:01, 10.62it/s]
Total progress: 32%|███▏ | 6/19 [00:00<00:00, 14.59it/s][A
37%|███▋ | 7/19 [00:00<00:01, 10.58it/s]
Total progress: 42%|████▏ | 8/19 [00:00<00:00, 12.81it/s][A
47%|████▋ | 9/19 [00:00<00:00, 10.56it/s]
Total progress: 53%|█████▎ | 10/19 [00:00<00:00, 11.95it/s][A
58%|█████▊ | 11/19 [00:01<00:00, 10.50it/s]
Total progress: 63%|██████▎ | 12/19 [00:00<00:00, 11.32it/s][A
68%|██████▊ | 13/19 [00:01<00:00, 10.28it/s]
Total progress: 74%|███████▎ | 14/19 [00:01<00:00, 10.82it/s][A
79%|███████▉ | 15/19 [00:01<00:00, 10.14it/s]
Total progress: 84%|████████▍ | 16/19 [00:01<00:00, 10.50it/s][A
89%|████████▉ | 17/19 [00:01<00:00, 10.05it/s]
Total progress: 95%|█████████▍| 18/19 [00:01<00:00, 10.30it/s][A
100%|██████████| 19/19 [00:01<00:00, 10.00it/s]
100%|██████████| 19/19 [00:01<00:00, 10.14it/s]
[Unload] Trying to free 1089.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 3346.57 MB ... Done.
Total progress: 100%|██████████| 19/19 [00:01<00:00, 10.30it/s][A
Total progress: 100%|██████████| 19/19 [00:01<00:00, 10.19it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 3346.63 MB ... Unload model JointTextEncoder Current free memory is 5111.99 MB ... Unload model KModel Current free memory is 10109.21 MB ... Unload model IntegratedAutoencoderKL Done.
################################################################
[1m[32mInstall script for stable-diffusion + Web UI
[1m[34mTested on Debian 11 (Bullseye), Fedora 34+ and openSUSE Leap 15.4 or newer.[0m
################################################################
################################################################
Running on [1m[32mroot[0m user
################################################################
################################################################
Repo already cloned, using it as install directory
################################################################
################################################################
Create and activate python venv
################################################################
################################################################
Launching launch.py...
################################################################
glibc version is 2.39
Check TCMalloc: libtcmalloc_minimal.so.4
libtcmalloc_minimal.so.4 is linked with libc.so,execute LD_PRELOAD=/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4
=============================================================================================
INCOMPATIBLE PYTHON VERSION
This program is tested with 3.10.6 Python, but you have 3.12.3.
If you encounter an error with "RuntimeError: Couldn't install torch." message,
or any other error regarding unsuccessful package (library) installation,
please downgrade (or upgrade) to the latest version of 3.10 Python
and delete current Python and "venv" folder in WebUI's directory.
You can download 3.10 Python from here: https://www.python.org/downloads/release/python-3106/
Use --skip-python-version-check to suppress this warning.
=============================================================================================
Python 3.12.3 (main, Jan 22 2026, 20:57:42) [GCC 13.3.0]
Version: f2.0.1v1.10.1-previous-669-gdfdcbab6
Commit hash: dfdcbab685e57677014f05a3309b48cc87383167
Legacy Preprocessor init warning: Unable to install insightface automatically. Please try run `pip install insightface` manually.
Launching Web UI with arguments: -f --listen --api --enable-insecure-extension-access --xformers --no-half-vae --port 7887
Total VRAM 20017 MB, total RAM 64105 MB
pytorch version: 2.3.1+cu121
WARNING:xformers:A matching Triton is not available, some optimizations will not be enabled
Traceback (most recent call last):
File "/opt/sd-webui/venv/lib/python3.12/site-packages/xformers/__init__.py", line 57, in _is_triton_available
import triton # noqa
^^^^^^^^^^^^^
ModuleNotFoundError: No module named 'triton'
xformers version: 0.0.27
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA RTX 4000 SFF Ada Generation : native
Hint: your device supports --cuda-malloc for potential speed improvements.
VAE dtype preferences: [torch.bfloat16, torch.float32] -> torch.bfloat16
CUDA Using Stream: False
Using xformers cross attention
Using xformers attention for VAE
ControlNet preprocessor location: /opt/sd-webui/models/ControlNetPreprocessor
*** Error loading script: soft_inpainting.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 525, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/sd-webui/modules/script_loading.py", line 13, in load_module
module_spec.loader.exec_module(module)
File "<frozen importlib._bootstrap_external>", line 995, in exec_module
File "<frozen importlib._bootstrap>", line 488, in _call_with_frames_removed
File "/opt/sd-webui/extensions-builtin/soft-inpainting/scripts/soft_inpainting.py", line 10, in <module>
from joblib import Parallel, delayed, cpu_count
ModuleNotFoundError: No module named 'joblib'
---
2026-02-12 07:37:28,651 - ControlNet - [0;32mINFO[0m - ControlNet UI callback registered.
Model selected: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
Using online LoRAs in FP16: False
Running on local URL: http://0.0.0.0:7887
To create a public link, set `share=True` in `launch()`.
Startup time: 7.5s (prepare environment: 1.1s, launcher: 0.2s, import torch: 3.1s, other imports: 0.1s, load scripts: 0.7s, create ui: 1.1s, gradio launch: 0.5s, add APIs: 0.7s).
Loading Model: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Done.
StateDict Keys: {'unet': 1680, 'vae': 248, 'text_encoder': 197, 'text_encoder_2': 518, 'ignore': 0}
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
K-Model Created: {'storage_dtype': torch.float16, 'computation_dtype': torch.float16}
Model loaded in 0.5s (unload existing model: 0.1s, forge model load: 0.3s).
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 1231.42 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 10312.25 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 9128.69 MB, All loaded to GPU.
Moving model(s) has taken 0.06 seconds
[Unload] Trying to free 3051.58 MB for cuda:0 with 0 models keep loaded ... Current free memory is 10137.36 MB ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 10137.36 MB, Model Require: 1559.68 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 7553.68 MB, All loaded to GPU.
Moving model(s) has taken 0.87 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 8352.66 MB ... Done.
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 8351.98 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 8351.98 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 2430.93 MB, All loaded to GPU.
Moving model(s) has taken 3.25 seconds
0%| | 0/19 [00:00<?, ?it/s]
Total progress: 0%| | 0/19 [00:00<?, ?it/s][A
5%|▌ | 1/19 [00:00<00:02, 6.86it/s]
Total progress: 16%|█▌ | 3/19 [00:00<00:00, 26.47it/s][A
16%|█▌ | 3/19 [00:00<00:01, 10.63it/s]
26%|██▋ | 5/19 [00:00<00:01, 11.28it/s]
Total progress: 32%|███▏ | 6/19 [00:00<00:00, 15.45it/s][A
37%|███▋ | 7/19 [00:00<00:01, 11.11it/s]
Total progress: 42%|████▏ | 8/19 [00:00<00:00, 13.42it/s][A
47%|████▋ | 9/19 [00:00<00:00, 11.00it/s]
Total progress: 53%|█████▎ | 10/19 [00:00<00:00, 12.37it/s][A
58%|█████▊ | 11/19 [00:01<00:00, 10.81it/s]
Total progress: 63%|██████▎ | 12/19 [00:00<00:00, 11.63it/s][A
68%|██████▊ | 13/19 [00:01<00:00, 10.48it/s]
Total progress: 74%|███████▎ | 14/19 [00:01<00:00, 11.00it/s][A
79%|███████▉ | 15/19 [00:01<00:00, 10.27it/s]
Total progress: 84%|████████▍ | 16/19 [00:01<00:00, 10.62it/s][A
89%|████████▉ | 17/19 [00:01<00:00, 10.14it/s]
Total progress: 95%|█████████▍| 18/19 [00:01<00:00, 10.37it/s][A
100%|██████████| 19/19 [00:01<00:00, 10.05it/s]
100%|██████████| 19/19 [00:01<00:00, 10.35it/s]
[Unload] Trying to free 1089.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 3346.57 MB ... Done.
Total progress: 100%|██████████| 19/19 [00:01<00:00, 10.37it/s][A
Total progress: 100%|██████████| 19/19 [00:01<00:00, 10.36it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 3346.63 MB ... Unload model JointTextEncoder Current free memory is 5111.99 MB ... Unload model KModel Current free memory is 10109.21 MB ... Unload model IntegratedAutoencoderKL Done.
################################################################
[1m[32mInstall script for stable-diffusion + Web UI
[1m[34mTested on Debian 11 (Bullseye), Fedora 34+ and openSUSE Leap 15.4 or newer.[0m
################################################################
################################################################
Running on [1m[32mroot[0m user
################################################################
################################################################
Repo already cloned, using it as install directory
################################################################
################################################################
Create and activate python venv
################################################################
################################################################
Launching launch.py...
################################################################
glibc version is 2.39
Check TCMalloc: libtcmalloc_minimal.so.4
libtcmalloc_minimal.so.4 is linked with libc.so,execute LD_PRELOAD=/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4
=============================================================================================
INCOMPATIBLE PYTHON VERSION
This program is tested with 3.10.6 Python, but you have 3.12.3.
If you encounter an error with "RuntimeError: Couldn't install torch." message,
or any other error regarding unsuccessful package (library) installation,
please downgrade (or upgrade) to the latest version of 3.10 Python
and delete current Python and "venv" folder in WebUI's directory.
You can download 3.10 Python from here: https://www.python.org/downloads/release/python-3106/
Use --skip-python-version-check to suppress this warning.
=============================================================================================
Python 3.12.3 (main, Jan 22 2026, 20:57:42) [GCC 13.3.0]
Version: f2.0.1v1.10.1-previous-669-gdfdcbab6
Commit hash: dfdcbab685e57677014f05a3309b48cc87383167
Legacy Preprocessor init warning: Unable to install insightface automatically. Please try run `pip install insightface` manually.
Launching Web UI with arguments: -f --listen --api --enable-insecure-extension-access --xformers --no-half-vae --port 7887
Total VRAM 20017 MB, total RAM 64105 MB
pytorch version: 2.3.1+cu121
WARNING:xformers:A matching Triton is not available, some optimizations will not be enabled
Traceback (most recent call last):
File "/opt/sd-webui/venv/lib/python3.12/site-packages/xformers/__init__.py", line 57, in _is_triton_available
import triton # noqa
^^^^^^^^^^^^^
ModuleNotFoundError: No module named 'triton'
xformers version: 0.0.27
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA RTX 4000 SFF Ada Generation : native
Hint: your device supports --cuda-malloc for potential speed improvements.
VAE dtype preferences: [torch.bfloat16, torch.float32] -> torch.bfloat16
CUDA Using Stream: False
Using xformers cross attention
Using xformers attention for VAE
ControlNet preprocessor location: /opt/sd-webui/models/ControlNetPreprocessor
*** Error loading script: soft_inpainting.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 525, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/sd-webui/modules/script_loading.py", line 13, in load_module
module_spec.loader.exec_module(module)
File "<frozen importlib._bootstrap_external>", line 995, in exec_module
File "<frozen importlib._bootstrap>", line 488, in _call_with_frames_removed
File "/opt/sd-webui/extensions-builtin/soft-inpainting/scripts/soft_inpainting.py", line 10, in <module>
from joblib import Parallel, delayed, cpu_count
ModuleNotFoundError: No module named 'joblib'
---
2026-02-12 08:05:32,023 - ControlNet - [0;32mINFO[0m - ControlNet UI callback registered.
Model selected: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
Using online LoRAs in FP16: False
Running on local URL: http://0.0.0.0:7887
To create a public link, set `share=True` in `launch()`.
Startup time: 9.2s (prepare environment: 1.4s, launcher: 0.2s, import torch: 3.6s, other imports: 0.1s, load scripts: 0.9s, create ui: 1.2s, gradio launch: 0.6s, add APIs: 1.1s).
Loading Model: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Done.
StateDict Keys: {'unet': 1680, 'vae': 248, 'text_encoder': 197, 'text_encoder_2': 518, 'ignore': 0}
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
K-Model Created: {'storage_dtype': torch.float16, 'computation_dtype': torch.float16}
Model loaded in 0.6s (unload existing model: 0.2s, forge model load: 0.4s).
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3051.58 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 10342.15 MB, Model Require: 1559.68 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 7758.47 MB, All loaded to GPU.
Moving model(s) has taken 0.72 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 8538.44 MB ... Done.
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 8537.77 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 8537.77 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 2616.72 MB, All loaded to GPU.
Moving model(s) has taken 3.31 seconds
0%| | 0/10 [00:00<?, ?it/s]
Total progress: 0%| | 0/10 [00:00<?, ?it/s][A
10%|█ | 1/10 [00:00<00:02, 4.38it/s]
Total progress: 30%|███ | 3/10 [00:00<00:00, 22.07it/s][A
30%|███ | 3/10 [00:00<00:00, 8.57it/s]
50%|█████ | 5/10 [00:00<00:00, 9.81it/s]
Total progress: 60%|██████ | 6/10 [00:00<00:00, 15.10it/s][A
70%|███████ | 7/10 [00:00<00:00, 10.09it/s]
Total progress: 80%|████████ | 8/10 [00:00<00:00, 13.05it/s][A
90%|█████████ | 9/10 [00:00<00:00, 10.27it/s]
Total progress: 100%|██████████| 10/10 [00:00<00:00, 12.11it/s][A
100%|██████████| 10/10 [00:01<00:00, 9.68it/s]
[Unload] Trying to free 1296.42 MB for cuda:0 with 0 models keep loaded ... Current free memory is 3522.31 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 3522.31 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 2338.75 MB, All loaded to GPU.
Moving model(s) has taken 0.10 seconds
Total progress: 100%|██████████| 10/10 [00:01<00:00, 12.11it/s][A
Total progress: 100%|██████████| 10/10 [00:01<00:00, 9.50it/s]
Model selected: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/ponyRealism_V22.safetensors', 'hash': 'd84eb26b'}, 'additional_modules': [], 'unet_storage_dtype': None}
Using online LoRAs in FP16: False
Loading Model: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/ponyRealism_V22.safetensors', 'hash': 'd84eb26b'}, 'additional_modules': [], 'unet_storage_dtype': None}
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 3351.30 MB ... Unload model JointTextEncoder Current free memory is 5111.66 MB ... Unload model KModel Current free memory is 10108.99 MB ... Unload model IntegratedAutoencoderKL Done.
StateDict Keys: {'unet': 1680, 'vae': 248, 'text_encoder': 197, 'text_encoder_2': 518, 'ignore': 0}
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
K-Model Created: {'storage_dtype': torch.float16, 'computation_dtype': torch.float16}
Model loaded in 5.8s (unload existing model: 4.9s, forge model load: 0.9s).
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[LORA] Loaded /opt/sd-webui/models/Lora/Octi_20260206_230414.safetensors for KModel-UNet with 722 keys at weight 0.8 (skipped 0 keys) with on_the_fly = False
[LORA] Loaded /opt/sd-webui/models/Lora/Octi_20260206_230414.safetensors for KModel-CLIP with 264 keys at weight 0.8 (skipped 0 keys) with on_the_fly = False
[Unload] Trying to free 3051.58 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 10274.02 MB, Model Require: 1559.68 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 7690.34 MB, All loaded to GPU.
Moving model(s) has taken 1.69 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 8515.82 MB ... Done.
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 8515.14 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 8515.14 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 2594.10 MB, All loaded to GPU.
Moving model(s) has taken 5.30 seconds
0%| | 0/10 [00:00<?, ?it/s]
Total progress: 0%| | 0/10 [00:00<?, ?it/s][A
20%|██ | 2/10 [00:00<00:00, 13.17it/s]
Total progress: 30%|███ | 3/10 [00:00<00:00, 20.46it/s][A
40%|████ | 4/10 [00:00<00:00, 13.37it/s]
Total progress: 60%|██████ | 6/10 [00:00<00:00, 14.81it/s][A
60%|██████ | 6/10 [00:00<00:00, 12.33it/s]
Total progress: 80%|████████ | 8/10 [00:00<00:00, 13.03it/s][A
80%|████████ | 8/10 [00:00<00:00, 11.59it/s]
Total progress: 100%|██████████| 10/10 [00:00<00:00, 12.03it/s][A
100%|██████████| 10/10 [00:00<00:00, 11.13it/s]
100%|██████████| 10/10 [00:00<00:00, 11.66it/s]
[Unload] Trying to free 1296.42 MB for cuda:0 with 0 models keep loaded ... Current free memory is 3537.72 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 3537.72 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 2354.16 MB, All loaded to GPU.
Moving model(s) has taken 0.08 seconds
Model selected: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
Using online LoRAs in FP16: False
Total progress: 100%|██████████| 10/10 [00:01<00:00, 12.03it/s][A
Total progress: 100%|██████████| 10/10 [00:01<00:00, 9.74it/s]
Model selected: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/ponyRealism_V22.safetensors', 'hash': 'd84eb26b'}, 'additional_modules': [], 'unet_storage_dtype': None}
Using online LoRAs in FP16: False
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 3375.34 MB ... Unload model JointTextEncoder Current free memory is 5132.32 MB ... Unload model KModel Current free memory is 10109.62 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 10272.06 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 7495.08 MB, All loaded to GPU.
Moving model(s) has taken 1.13 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 8513.94 MB ... Done.
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 8513.27 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 8513.27 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 2592.22 MB, All loaded to GPU.
Moving model(s) has taken 3.03 seconds
0%| | 0/12 [00:00<?, ?it/s]
Total progress: 0%| | 0/12 [00:00<?, ?it/s][A
17%|█▋ | 2/12 [00:00<00:00, 13.61it/s]
Total progress: 25%|██▌ | 3/12 [00:00<00:00, 20.48it/s][A
33%|███▎ | 4/12 [00:00<00:00, 13.61it/s]
Total progress: 50%|█████ | 6/12 [00:00<00:00, 14.95it/s][A
50%|█████ | 6/12 [00:00<00:00, 12.50it/s]
Total progress: 67%|██████▋ | 8/12 [00:00<00:00, 13.07it/s][A
67%|██████▋ | 8/12 [00:00<00:00, 11.67it/s]
Total progress: 83%|████████▎ | 10/12 [00:00<00:00, 12.04it/s][A
83%|████████▎ | 10/12 [00:00<00:00, 11.19it/s]
Total progress: 100%|██████████| 12/12 [00:00<00:00, 11.47it/s][A
100%|██████████| 12/12 [00:01<00:00, 10.95it/s]
100%|██████████| 12/12 [00:01<00:00, 11.53it/s]
[Unload] Trying to free 1296.42 MB for cuda:0 with 0 models keep loaded ... Current free memory is 3512.76 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 3512.76 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 2329.20 MB, All loaded to GPU.
Moving model(s) has taken 0.07 seconds
Model selected: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
Using online LoRAs in FP16: False
Total progress: 100%|██████████| 12/12 [00:01<00:00, 11.47it/s][A
Total progress: 100%|██████████| 12/12 [00:01<00:00, 9.95it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 3349.75 MB ... Unload model JointTextEncoder Current free memory is 5108.61 MB ... Unload model KModel Current free memory is 10108.99 MB ... Unload model IntegratedAutoencoderKL Done.
################################################################
[1m[32mInstall script for stable-diffusion + Web UI
[1m[34mTested on Debian 11 (Bullseye), Fedora 34+ and openSUSE Leap 15.4 or newer.[0m
################################################################
################################################################
Running on [1m[32mroot[0m user
################################################################
################################################################
Repo already cloned, using it as install directory
################################################################
################################################################
Create and activate python venv
################################################################
################################################################
Launching launch.py...
################################################################
glibc version is 2.39
Check TCMalloc: libtcmalloc_minimal.so.4
libtcmalloc_minimal.so.4 is linked with libc.so,execute LD_PRELOAD=/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4
=============================================================================================
INCOMPATIBLE PYTHON VERSION
This program is tested with 3.10.6 Python, but you have 3.12.3.
If you encounter an error with "RuntimeError: Couldn't install torch." message,
or any other error regarding unsuccessful package (library) installation,
please downgrade (or upgrade) to the latest version of 3.10 Python
and delete current Python and "venv" folder in WebUI's directory.
You can download 3.10 Python from here: https://www.python.org/downloads/release/python-3106/
Use --skip-python-version-check to suppress this warning.
=============================================================================================
Python 3.12.3 (main, Jan 22 2026, 20:57:42) [GCC 13.3.0]
Version: f2.0.1v1.10.1-previous-669-gdfdcbab6
Commit hash: dfdcbab685e57677014f05a3309b48cc87383167
Legacy Preprocessor init warning: Unable to install insightface automatically. Please try run `pip install insightface` manually.
Launching Web UI with arguments: -f --listen --api --enable-insecure-extension-access --xformers --no-half-vae --port 7887
Total VRAM 20017 MB, total RAM 64105 MB
pytorch version: 2.3.1+cu121
WARNING:xformers:A matching Triton is not available, some optimizations will not be enabled
Traceback (most recent call last):
File "/opt/sd-webui/venv/lib/python3.12/site-packages/xformers/__init__.py", line 57, in _is_triton_available
import triton # noqa
^^^^^^^^^^^^^
ModuleNotFoundError: No module named 'triton'
xformers version: 0.0.27
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA RTX 4000 SFF Ada Generation : native
Hint: your device supports --cuda-malloc for potential speed improvements.
VAE dtype preferences: [torch.bfloat16, torch.float32] -> torch.bfloat16
CUDA Using Stream: False
Using xformers cross attention
Using xformers attention for VAE
ControlNet preprocessor location: /opt/sd-webui/models/ControlNetPreprocessor
*** Error loading script: soft_inpainting.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 525, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/sd-webui/modules/script_loading.py", line 13, in load_module
module_spec.loader.exec_module(module)
File "<frozen importlib._bootstrap_external>", line 995, in exec_module
File "<frozen importlib._bootstrap>", line 488, in _call_with_frames_removed
File "/opt/sd-webui/extensions-builtin/soft-inpainting/scripts/soft_inpainting.py", line 10, in <module>
from joblib import Parallel, delayed, cpu_count
ModuleNotFoundError: No module named 'joblib'
---
2026-02-12 08:25:28,750 - ControlNet - [0;32mINFO[0m - ControlNet UI callback registered.
Model selected: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
Using online LoRAs in FP16: False
Running on local URL: http://0.0.0.0:7887
To create a public link, set `share=True` in `launch()`.
Loading Model: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Done.
Startup time: 10.1s (prepare environment: 1.4s, launcher: 0.3s, import torch: 4.5s, other imports: 0.2s, load scripts: 1.0s, create ui: 1.2s, gradio launch: 0.5s, add APIs: 1.0s).
StateDict Keys: {'unet': 1680, 'vae': 248, 'text_encoder': 197, 'text_encoder_2': 518, 'ignore': 0}
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
K-Model Created: {'storage_dtype': torch.float16, 'computation_dtype': torch.float16}
Model loaded in 1.0s (unload existing model: 0.2s, forge model load: 0.8s).
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
*** Error running process: /opt/sd-webui/extensions-builtin/sd_forge_neveroom/scripts/forge_never_oom.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 844, in process
script.process(p, *script_args)
File "/opt/sd-webui/extensions-builtin/sd_forge_neveroom/scripts/forge_never_oom.py", line 27, in process
unet_enabled, vae_enabled = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 2, got 0)
---
[Unload] Trying to free 3051.58 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 10342.15 MB, Model Require: 1559.68 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 7758.47 MB, All loaded to GPU.
Moving model(s) has taken 0.74 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 8538.44 MB ... Done.
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_dynamic_thresholding/scripts/forge_dynamic_thresholding.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_dynamic_thresholding/scripts/forge_dynamic_thresholding.py", line 49, in process_before_every_sampling
enabled, mimic_scale, threshold_percentile, mimic_mode, mimic_scale_min, cfg_mode, cfg_scale_min, \
ValueError: not enough values to unpack (expected 12, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_freeu/scripts/forge_freeu.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_freeu/scripts/forge_freeu.py", line 143, in process_before_every_sampling
freeu_enabled, freeu_b1, freeu_b2, freeu_s1, freeu_s2, freeu_start, freeu_end = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 7, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_kohya_hrfix/scripts/kohya_hrfix.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_kohya_hrfix/scripts/kohya_hrfix.py", line 79, in process_before_every_sampling
enabled, block_number, downscale_factor, start_percent, end_percent, downscale_after_skip, downscale_method, upscale_method = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 8, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_latent_modifier/scripts/forge_latent_modifier.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_latent_modifier/scripts/forge_latent_modifier.py", line 96, in process_before_every_sampling
enabled, sharpness_multiplier, sharpness_method, tonemap_multiplier, tonemap_method, tonemap_percentile, contrast_multiplier, combat_method, combat_cfg_drift, rescale_cfg_phi, extra_noise_type, extra_noise_method, extra_noise_multiplier, extra_noise_lowpass, divisive_norm_size, divisive_norm_multiplier, spectral_mod_mode, spectral_mod_percentile, spectral_mod_multiplier, affect_uncond, dyn_cfg_augmentation = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 21, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_multidiffusion/scripts/forge_multidiffusion.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_multidiffusion/scripts/forge_multidiffusion.py", line 36, in process_before_every_sampling
enabled, method, tile_width, tile_height, tile_overlap, tile_batch_size = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 6, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_perturbed_attention/scripts/forge_perturbed_attention.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_perturbed_attention/scripts/forge_perturbed_attention.py", line 50, in process_before_every_sampling
enabled, scale, attenuation, start_step, end_step = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 5, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_sag/scripts/forge_sag.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_sag/scripts/forge_sag.py", line 197, in process_before_every_sampling
enabled, scale, blur_sigma, threshold = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 4, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_stylealign/scripts/forge_stylealign.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_stylealign/scripts/forge_stylealign.py", line 33, in process_before_every_sampling
shared_attention, strength = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 2, got 0)
---
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 8537.77 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 8537.77 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 2616.72 MB, All loaded to GPU.
Moving model(s) has taken 3.19 seconds
0%| | 0/20 [00:00<?, ?it/s]
Total progress: 0%| | 0/20 [00:00<?, ?it/s][A
5%|▌ | 1/20 [00:00<00:03, 5.43it/s]
Total progress: 15%|█▌ | 3/20 [00:00<00:00, 24.04it/s][A
15%|█▌ | 3/20 [00:00<00:01, 8.99it/s]
25%|██▌ | 5/20 [00:00<00:01, 9.87it/s]
Total progress: 30%|███ | 6/20 [00:00<00:00, 14.06it/s][A
35%|███▌ | 7/20 [00:00<00:01, 10.23it/s]
Total progress: 40%|████ | 8/20 [00:00<00:00, 12.65it/s][A
45%|████▌ | 9/20 [00:00<00:01, 10.35it/s]
Total progress: 50%|█████ | 10/20 [00:00<00:00, 11.82it/s][A
55%|█████▌ | 11/20 [00:01<00:00, 10.26it/s]
Total progress: 60%|██████ | 12/20 [00:00<00:00, 11.15it/s][A
65%|██████▌ | 13/20 [00:01<00:00, 10.13it/s]
Total progress: 70%|███████ | 14/20 [00:01<00:00, 10.71it/s][A
75%|███████▌ | 15/20 [00:01<00:00, 10.05it/s]
Total progress: 80%|████████ | 16/20 [00:01<00:00, 10.45it/s][A
85%|████████▌ | 17/20 [00:01<00:00, 10.08it/s]
Total progress: 90%|█████████ | 18/20 [00:01<00:00, 10.38it/s][A
95%|█████████▌| 19/20 [00:01<00:00, 10.18it/s]
Total progress: 100%|██████████| 20/20 [00:01<00:00, 10.39it/s][A
100%|██████████| 20/20 [00:02<00:00, 9.99it/s]
[Unload] Trying to free 1296.42 MB for cuda:0 with 0 models keep loaded ... Current free memory is 3522.31 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 3522.31 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 2338.75 MB, All loaded to GPU.
Moving model(s) has taken 0.09 seconds
Total progress: 100%|██████████| 20/20 [00:02<00:00, 10.39it/s][A
Total progress: 100%|██████████| 20/20 [00:02<00:00, 9.70it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 3351.30 MB ... Unload model JointTextEncoder Current free memory is 5111.66 MB ... Unload model KModel Current free memory is 10108.99 MB ... Unload model IntegratedAutoencoderKL Done.
################################################################
[1m[32mInstall script for stable-diffusion + Web UI
[1m[34mTested on Debian 11 (Bullseye), Fedora 34+ and openSUSE Leap 15.4 or newer.[0m
################################################################
################################################################
Running on [1m[32mroot[0m user
################################################################
################################################################
Repo already cloned, using it as install directory
################################################################
################################################################
Create and activate python venv
################################################################
################################################################
Launching launch.py...
################################################################
glibc version is 2.39
Check TCMalloc: libtcmalloc_minimal.so.4
libtcmalloc_minimal.so.4 is linked with libc.so,execute LD_PRELOAD=/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4
=============================================================================================
INCOMPATIBLE PYTHON VERSION
This program is tested with 3.10.6 Python, but you have 3.12.3.
If you encounter an error with "RuntimeError: Couldn't install torch." message,
or any other error regarding unsuccessful package (library) installation,
please downgrade (or upgrade) to the latest version of 3.10 Python
and delete current Python and "venv" folder in WebUI's directory.
You can download 3.10 Python from here: https://www.python.org/downloads/release/python-3106/
Use --skip-python-version-check to suppress this warning.
=============================================================================================
Python 3.12.3 (main, Jan 22 2026, 20:57:42) [GCC 13.3.0]
Version: f2.0.1v1.10.1-previous-669-gdfdcbab6
Commit hash: dfdcbab685e57677014f05a3309b48cc87383167
Legacy Preprocessor init warning: Unable to install insightface automatically. Please try run `pip install insightface` manually.
Launching Web UI with arguments: -f --listen --api --enable-insecure-extension-access --xformers --no-half-vae --port 7887
Total VRAM 20017 MB, total RAM 64105 MB
pytorch version: 2.3.1+cu121
WARNING:xformers:A matching Triton is not available, some optimizations will not be enabled
Traceback (most recent call last):
File "/opt/sd-webui/venv/lib/python3.12/site-packages/xformers/__init__.py", line 57, in _is_triton_available
import triton # noqa
^^^^^^^^^^^^^
ModuleNotFoundError: No module named 'triton'
xformers version: 0.0.27
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA RTX 4000 SFF Ada Generation : native
Hint: your device supports --cuda-malloc for potential speed improvements.
VAE dtype preferences: [torch.bfloat16, torch.float32] -> torch.bfloat16
CUDA Using Stream: False
Using xformers cross attention
Using xformers attention for VAE
ControlNet preprocessor location: /opt/sd-webui/models/ControlNetPreprocessor
*** Error loading script: soft_inpainting.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 525, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/sd-webui/modules/script_loading.py", line 13, in load_module
module_spec.loader.exec_module(module)
File "<frozen importlib._bootstrap_external>", line 995, in exec_module
File "<frozen importlib._bootstrap>", line 488, in _call_with_frames_removed
File "/opt/sd-webui/extensions-builtin/soft-inpainting/scripts/soft_inpainting.py", line 10, in <module>
from joblib import Parallel, delayed, cpu_count
ModuleNotFoundError: No module named 'joblib'
---
2026-02-13 08:09:14,705 - ControlNet - [0;32mINFO[0m - ControlNet UI callback registered.
Model selected: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
Using online LoRAs in FP16: False
Running on local URL: http://0.0.0.0:7887
To create a public link, set `share=True` in `launch()`.
Loading Model: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Done.
Startup time: 9.5s (prepare environment: 1.9s, launcher: 0.3s, import torch: 3.8s, other imports: 0.2s, load scripts: 0.8s, create ui: 1.1s, gradio launch: 0.5s, add APIs: 0.9s).
StateDict Keys: {'unet': 1680, 'vae': 248, 'text_encoder': 197, 'text_encoder_2': 518, 'ignore': 0}
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
K-Model Created: {'storage_dtype': torch.float16, 'computation_dtype': torch.float16}
Model loaded in 1.5s (unload existing model: 0.1s, forge model load: 1.3s).
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3051.58 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 9057.02 MB, Model Require: 1559.68 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 6473.34 MB, All loaded to GPU.
Moving model(s) has taken 1.23 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 7253.32 MB ... Done.
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 7252.64 MB ... Unload model JointTextEncoder Done.
[Memory Management] Target: KModel, Free GPU: 9013.00 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3091.95 MB, All loaded to GPU.
Moving model(s) has taken 5.78 seconds
0%| | 0/20 [00:00<?, ?it/s]
Total progress: 0%| | 0/20 [00:00<?, ?it/s][A
5%|▌ | 1/20 [00:00<00:09, 1.96it/s]
Total progress: 15%|█▌ | 3/20 [00:00<00:00, 23.05it/s][A
15%|█▌ | 3/20 [00:00<00:03, 5.19it/s]
25%|██▌ | 5/20 [00:00<00:02, 7.28it/s]
Total progress: 30%|███ | 6/20 [00:00<00:00, 14.85it/s][A
35%|███▌ | 7/20 [00:01<00:01, 8.36it/s]
Total progress: 40%|████ | 8/20 [00:00<00:00, 12.90it/s][A
45%|████▌ | 9/20 [00:01<00:01, 9.08it/s]
Total progress: 50%|█████ | 10/20 [00:00<00:00, 12.02it/s][A
55%|█████▌ | 11/20 [00:01<00:00, 9.52it/s]
Total progress: 60%|██████ | 12/20 [00:00<00:00, 11.44it/s][A
65%|██████▌ | 13/20 [00:01<00:00, 9.67it/s]
Total progress: 70%|███████ | 14/20 [00:01<00:00, 10.89it/s][A
75%|███████▌ | 15/20 [00:01<00:00, 9.73it/s]
Total progress: 80%|████████ | 16/20 [00:01<00:00, 10.55it/s][A
85%|████████▌ | 17/20 [00:02<00:00, 9.77it/s]
Total progress: 90%|█████████ | 18/20 [00:01<00:00, 10.32it/s][A
95%|█████████▌| 19/20 [00:02<00:00, 9.79it/s]
Total progress: 100%|██████████| 20/20 [00:01<00:00, 10.17it/s][A
100%|██████████| 20/20 [00:02<00:00, 9.80it/s]
100%|██████████| 20/20 [00:02<00:00, 8.60it/s]
[Unload] Trying to free 1296.42 MB for cuda:0 with 0 models keep loaded ... Current free memory is 3995.88 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 3995.88 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 2812.32 MB, All loaded to GPU.
Moving model(s) has taken 0.08 seconds
Total progress: 100%|██████████| 20/20 [00:02<00:00, 10.17it/s][A
Total progress: 100%|██████████| 20/20 [00:02<00:00, 9.55it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 3823.93 MB ... Unload model KModel Current free memory is 8822.92 MB ... Unload model IntegratedAutoencoderKL Done.
################################################################
[1m[32mInstall script for stable-diffusion + Web UI
[1m[34mTested on Debian 11 (Bullseye), Fedora 34+ and openSUSE Leap 15.4 or newer.[0m
################################################################
################################################################
Running on [1m[32mroot[0m user
################################################################
################################################################
Repo already cloned, using it as install directory
################################################################
################################################################
Create and activate python venv
################################################################
################################################################
Launching launch.py...
################################################################
glibc version is 2.39
Check TCMalloc: libtcmalloc_minimal.so.4
libtcmalloc_minimal.so.4 is linked with libc.so,execute LD_PRELOAD=/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4
=============================================================================================
INCOMPATIBLE PYTHON VERSION
This program is tested with 3.10.6 Python, but you have 3.12.3.
If you encounter an error with "RuntimeError: Couldn't install torch." message,
or any other error regarding unsuccessful package (library) installation,
please downgrade (or upgrade) to the latest version of 3.10 Python
and delete current Python and "venv" folder in WebUI's directory.
You can download 3.10 Python from here: https://www.python.org/downloads/release/python-3106/
Use --skip-python-version-check to suppress this warning.
=============================================================================================
Python 3.12.3 (main, Jan 22 2026, 20:57:42) [GCC 13.3.0]
Version: f2.0.1v1.10.1-previous-669-gdfdcbab6
Commit hash: dfdcbab685e57677014f05a3309b48cc87383167
Legacy Preprocessor init warning: Unable to install insightface automatically. Please try run `pip install insightface` manually.
Launching Web UI with arguments: -f --listen --api --enable-insecure-extension-access --xformers --no-half-vae --port 7887
Total VRAM 20017 MB, total RAM 64105 MB
pytorch version: 2.3.1+cu121
WARNING:xformers:A matching Triton is not available, some optimizations will not be enabled
Traceback (most recent call last):
File "/opt/sd-webui/venv/lib/python3.12/site-packages/xformers/__init__.py", line 57, in _is_triton_available
import triton # noqa
^^^^^^^^^^^^^
ModuleNotFoundError: No module named 'triton'
xformers version: 0.0.27
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA RTX 4000 SFF Ada Generation : native
Hint: your device supports --cuda-malloc for potential speed improvements.
VAE dtype preferences: [torch.bfloat16, torch.float32] -> torch.bfloat16
CUDA Using Stream: False
Using xformers cross attention
Using xformers attention for VAE
ControlNet preprocessor location: /opt/sd-webui/models/ControlNetPreprocessor
*** Error loading script: soft_inpainting.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 525, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/sd-webui/modules/script_loading.py", line 13, in load_module
module_spec.loader.exec_module(module)
File "<frozen importlib._bootstrap_external>", line 995, in exec_module
File "<frozen importlib._bootstrap>", line 488, in _call_with_frames_removed
File "/opt/sd-webui/extensions-builtin/soft-inpainting/scripts/soft_inpainting.py", line 10, in <module>
from joblib import Parallel, delayed, cpu_count
ModuleNotFoundError: No module named 'joblib'
---
2026-02-13 08:13:59,268 - ControlNet - [0;32mINFO[0m - ControlNet UI callback registered.
Model selected: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
Using online LoRAs in FP16: False
Running on local URL: http://0.0.0.0:7887
To create a public link, set `share=True` in `launch()`.
Loading Model: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Done.
Startup time: 8.9s (prepare environment: 1.2s, launcher: 0.2s, import torch: 3.9s, other imports: 0.1s, load scripts: 0.8s, create ui: 1.1s, gradio launch: 0.5s, add APIs: 1.0s).
StateDict Keys: {'unet': 1680, 'vae': 248, 'text_encoder': 197, 'text_encoder_2': 518, 'ignore': 0}
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
K-Model Created: {'storage_dtype': torch.float16, 'computation_dtype': torch.float16}
Model loaded in 1.4s (unload existing model: 0.2s, forge model load: 1.2s).
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
*** Error running process: /opt/sd-webui/extensions-builtin/sd_forge_neveroom/scripts/forge_never_oom.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 844, in process
script.process(p, *script_args)
File "/opt/sd-webui/extensions-builtin/sd_forge_neveroom/scripts/forge_never_oom.py", line 27, in process
unet_enabled, vae_enabled = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 2, got 0)
---
[Unload] Trying to free 3051.58 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 9057.02 MB, Model Require: 1559.68 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 6473.34 MB, All loaded to GPU.
Moving model(s) has taken 0.76 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 7253.32 MB ... Done.
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_dynamic_thresholding/scripts/forge_dynamic_thresholding.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_dynamic_thresholding/scripts/forge_dynamic_thresholding.py", line 49, in process_before_every_sampling
enabled, mimic_scale, threshold_percentile, mimic_mode, mimic_scale_min, cfg_mode, cfg_scale_min, \
ValueError: not enough values to unpack (expected 12, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_freeu/scripts/forge_freeu.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_freeu/scripts/forge_freeu.py", line 143, in process_before_every_sampling
freeu_enabled, freeu_b1, freeu_b2, freeu_s1, freeu_s2, freeu_start, freeu_end = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 7, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_kohya_hrfix/scripts/kohya_hrfix.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_kohya_hrfix/scripts/kohya_hrfix.py", line 79, in process_before_every_sampling
enabled, block_number, downscale_factor, start_percent, end_percent, downscale_after_skip, downscale_method, upscale_method = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 8, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_latent_modifier/scripts/forge_latent_modifier.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_latent_modifier/scripts/forge_latent_modifier.py", line 96, in process_before_every_sampling
enabled, sharpness_multiplier, sharpness_method, tonemap_multiplier, tonemap_method, tonemap_percentile, contrast_multiplier, combat_method, combat_cfg_drift, rescale_cfg_phi, extra_noise_type, extra_noise_method, extra_noise_multiplier, extra_noise_lowpass, divisive_norm_size, divisive_norm_multiplier, spectral_mod_mode, spectral_mod_percentile, spectral_mod_multiplier, affect_uncond, dyn_cfg_augmentation = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 21, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_multidiffusion/scripts/forge_multidiffusion.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_multidiffusion/scripts/forge_multidiffusion.py", line 36, in process_before_every_sampling
enabled, method, tile_width, tile_height, tile_overlap, tile_batch_size = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 6, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_perturbed_attention/scripts/forge_perturbed_attention.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_perturbed_attention/scripts/forge_perturbed_attention.py", line 50, in process_before_every_sampling
enabled, scale, attenuation, start_step, end_step = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 5, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_sag/scripts/forge_sag.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_sag/scripts/forge_sag.py", line 197, in process_before_every_sampling
enabled, scale, blur_sigma, threshold = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 4, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_stylealign/scripts/forge_stylealign.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_stylealign/scripts/forge_stylealign.py", line 33, in process_before_every_sampling
shared_attention, strength = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 2, got 0)
---
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 7252.64 MB ... Unload model JointTextEncoder Done.
[Memory Management] Target: KModel, Free GPU: 9013.00 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3091.95 MB, All loaded to GPU.
Moving model(s) has taken 4.11 seconds
0%| | 0/20 [00:00<?, ?it/s]
Total progress: 0%| | 0/20 [00:00<?, ?it/s][A
5%|▌ | 1/20 [00:00<00:03, 5.48it/s]
Total progress: 15%|█▌ | 3/20 [00:00<00:00, 26.13it/s][A
15%|█▌ | 3/20 [00:00<00:01, 9.64it/s]
25%|██▌ | 5/20 [00:00<00:01, 10.14it/s]
Total progress: 30%|███ | 6/20 [00:00<00:00, 14.50it/s][A
35%|███▌ | 7/20 [00:00<00:01, 10.31it/s]
Total progress: 40%|████ | 8/20 [00:00<00:00, 12.78it/s][A
45%|████▌ | 9/20 [00:00<00:01, 10.41it/s]
Total progress: 50%|█████ | 10/20 [00:00<00:00, 11.92it/s][A
55%|█████▌ | 11/20 [00:01<00:00, 10.26it/s]
Total progress: 60%|██████ | 12/20 [00:00<00:00, 11.17it/s][A
65%|██████▌ | 13/20 [00:01<00:00, 10.12it/s]
Total progress: 70%|███████ | 14/20 [00:01<00:00, 10.71it/s][A
75%|███████▌ | 15/20 [00:01<00:00, 10.03it/s]
Total progress: 80%|████████ | 16/20 [00:01<00:00, 10.43it/s][A
85%|████████▌ | 17/20 [00:01<00:00, 9.98it/s]
Total progress: 90%|█████████ | 18/20 [00:01<00:00, 10.25it/s][A
90%|█████████ | 18/20 [00:01<00:00, 9.95it/s]
95%|█████████▌| 19/20 [00:01<00:00, 9.93it/s]
Total progress: 100%|██████████| 20/20 [00:01<00:00, 10.12it/s][A
100%|██████████| 20/20 [00:02<00:00, 9.92it/s]
100%|██████████| 20/20 [00:02<00:00, 9.93it/s]
[Unload] Trying to free 1296.42 MB for cuda:0 with 0 models keep loaded ... Current free memory is 3995.88 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 3995.88 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 2812.32 MB, All loaded to GPU.
Moving model(s) has taken 0.10 seconds
Total progress: 100%|██████████| 20/20 [00:02<00:00, 10.12it/s][A
Total progress: 100%|██████████| 20/20 [00:02<00:00, 9.61it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 3823.93 MB ... Unload model KModel Current free memory is 8822.92 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 8986.94 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 6209.96 MB, All loaded to GPU.
Moving model(s) has taken 0.84 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 7227.47 MB ... Done.
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 7226.79 MB ... Unload model JointTextEncoder Done.
[Memory Management] Target: KModel, Free GPU: 8985.65 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3064.60 MB, All loaded to GPU.
Moving model(s) has taken 2.42 seconds
0%| | 0/20 [00:00<?, ?it/s]
Total progress: 0%| | 0/20 [00:00<?, ?it/s][A
10%|█ | 2/20 [00:00<00:01, 13.23it/s]
Total progress: 15%|█▌ | 3/20 [00:00<00:00, 18.78it/s][A
20%|██ | 4/20 [00:00<00:01, 11.67it/s]
Total progress: 25%|██▌ | 5/20 [00:00<00:01, 13.73it/s][A
30%|███ | 6/20 [00:00<00:01, 11.09it/s]
Total progress: 35%|███▌ | 7/20 [00:00<00:01, 12.17it/s][A
40%|████ | 8/20 [00:00<00:01, 10.84it/s]
Total progress: 45%|████▌ | 9/20 [00:00<00:00, 11.50it/s][A
50%|█████ | 10/20 [00:00<00:00, 10.72it/s]
Total progress: 55%|█████▌ | 11/20 [00:00<00:00, 11.13it/s][A
60%|██████ | 12/20 [00:01<00:00, 10.47it/s]
Total progress: 65%|██████▌ | 13/20 [00:01<00:00, 10.69it/s][A
70%|███████ | 14/20 [00:01<00:00, 10.27it/s]
Total progress: 75%|███████▌ | 15/20 [00:01<00:00, 10.41it/s][A
80%|████████ | 16/20 [00:01<00:00, 10.14it/s]
Total progress: 85%|████████▌ | 17/20 [00:01<00:00, 10.24it/s][A
90%|█████████ | 18/20 [00:01<00:00, 10.06it/s]
Total progress: 95%|█████████▌| 19/20 [00:01<00:00, 10.13it/s][A
100%|██████████| 20/20 [00:01<00:00, 10.01it/s]
100%|██████████| 20/20 [00:01<00:00, 10.43it/s]
[Unload] Trying to free 1296.42 MB for cuda:0 with 0 models keep loaded ... Current free memory is 3986.53 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 3986.53 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 2802.97 MB, All loaded to GPU.
Moving model(s) has taken 0.10 seconds
Total progress: 100%|██████████| 20/20 [00:02<00:00, 10.13it/s][A
Total progress: 100%|██████████| 20/20 [00:02<00:00, 9.50it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 3822.58 MB ... Unload model KModel Current free memory is 8821.57 MB ... Unload model IntegratedAutoencoderKL Done.
################################################################
[1m[32mInstall script for stable-diffusion + Web UI
[1m[34mTested on Debian 11 (Bullseye), Fedora 34+ and openSUSE Leap 15.4 or newer.[0m
################################################################
################################################################
Running on [1m[32mroot[0m user
################################################################
################################################################
Repo already cloned, using it as install directory
################################################################
################################################################
Create and activate python venv
################################################################
################################################################
Launching launch.py...
################################################################
glibc version is 2.39
Check TCMalloc: libtcmalloc_minimal.so.4
libtcmalloc_minimal.so.4 is linked with libc.so,execute LD_PRELOAD=/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4
=============================================================================================
INCOMPATIBLE PYTHON VERSION
This program is tested with 3.10.6 Python, but you have 3.12.3.
If you encounter an error with "RuntimeError: Couldn't install torch." message,
or any other error regarding unsuccessful package (library) installation,
please downgrade (or upgrade) to the latest version of 3.10 Python
and delete current Python and "venv" folder in WebUI's directory.
You can download 3.10 Python from here: https://www.python.org/downloads/release/python-3106/
Use --skip-python-version-check to suppress this warning.
=============================================================================================
Python 3.12.3 (main, Jan 22 2026, 20:57:42) [GCC 13.3.0]
Version: f2.0.1v1.10.1-previous-669-gdfdcbab6
Commit hash: dfdcbab685e57677014f05a3309b48cc87383167
Legacy Preprocessor init warning: Unable to install insightface automatically. Please try run `pip install insightface` manually.
Launching Web UI with arguments: -f --listen --api --enable-insecure-extension-access --xformers --no-half-vae --port 7887
Total VRAM 20017 MB, total RAM 64105 MB
pytorch version: 2.3.1+cu121
WARNING:xformers:A matching Triton is not available, some optimizations will not be enabled
Traceback (most recent call last):
File "/opt/sd-webui/venv/lib/python3.12/site-packages/xformers/__init__.py", line 57, in _is_triton_available
import triton # noqa
^^^^^^^^^^^^^
ModuleNotFoundError: No module named 'triton'
xformers version: 0.0.27
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA RTX 4000 SFF Ada Generation : native
Hint: your device supports --cuda-malloc for potential speed improvements.
VAE dtype preferences: [torch.bfloat16, torch.float32] -> torch.bfloat16
CUDA Using Stream: False
Using xformers cross attention
Using xformers attention for VAE
ControlNet preprocessor location: /opt/sd-webui/models/ControlNetPreprocessor
*** Error loading script: soft_inpainting.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 525, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/sd-webui/modules/script_loading.py", line 13, in load_module
module_spec.loader.exec_module(module)
File "<frozen importlib._bootstrap_external>", line 995, in exec_module
File "<frozen importlib._bootstrap>", line 488, in _call_with_frames_removed
File "/opt/sd-webui/extensions-builtin/soft-inpainting/scripts/soft_inpainting.py", line 10, in <module>
from joblib import Parallel, delayed, cpu_count
ModuleNotFoundError: No module named 'joblib'
---
2026-02-26 10:46:05,591 - ControlNet - [0;32mINFO[0m - ControlNet UI callback registered.
Model selected: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
Using online LoRAs in FP16: False
Running on local URL: http://0.0.0.0:7887
To create a public link, set `share=True` in `launch()`.
Loading Model: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Done.
Startup time: 9.2s (prepare environment: 1.8s, launcher: 0.3s, import torch: 3.6s, other imports: 0.2s, load scripts: 0.8s, create ui: 1.1s, gradio launch: 0.5s, add APIs: 0.9s).
StateDict Keys: {'unet': 1680, 'vae': 248, 'text_encoder': 197, 'text_encoder_2': 518, 'ignore': 0}
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
K-Model Created: {'storage_dtype': torch.float16, 'computation_dtype': torch.float16}
Model loaded in 1.5s (unload existing model: 0.1s, forge model load: 1.3s).
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
*** Error running process: /opt/sd-webui/extensions-builtin/sd_forge_neveroom/scripts/forge_never_oom.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 844, in process
script.process(p, *script_args)
File "/opt/sd-webui/extensions-builtin/sd_forge_neveroom/scripts/forge_never_oom.py", line 27, in process
unet_enabled, vae_enabled = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 2, got 0)
---
[Unload] Trying to free 3051.58 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 9306.96 MB, Model Require: 1559.68 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 6723.28 MB, All loaded to GPU.
Moving model(s) has taken 0.93 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 7503.26 MB ... Done.
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_dynamic_thresholding/scripts/forge_dynamic_thresholding.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_dynamic_thresholding/scripts/forge_dynamic_thresholding.py", line 49, in process_before_every_sampling
enabled, mimic_scale, threshold_percentile, mimic_mode, mimic_scale_min, cfg_mode, cfg_scale_min, \
ValueError: not enough values to unpack (expected 12, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_freeu/scripts/forge_freeu.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_freeu/scripts/forge_freeu.py", line 143, in process_before_every_sampling
freeu_enabled, freeu_b1, freeu_b2, freeu_s1, freeu_s2, freeu_start, freeu_end = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 7, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_kohya_hrfix/scripts/kohya_hrfix.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_kohya_hrfix/scripts/kohya_hrfix.py", line 79, in process_before_every_sampling
enabled, block_number, downscale_factor, start_percent, end_percent, downscale_after_skip, downscale_method, upscale_method = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 8, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_latent_modifier/scripts/forge_latent_modifier.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_latent_modifier/scripts/forge_latent_modifier.py", line 96, in process_before_every_sampling
enabled, sharpness_multiplier, sharpness_method, tonemap_multiplier, tonemap_method, tonemap_percentile, contrast_multiplier, combat_method, combat_cfg_drift, rescale_cfg_phi, extra_noise_type, extra_noise_method, extra_noise_multiplier, extra_noise_lowpass, divisive_norm_size, divisive_norm_multiplier, spectral_mod_mode, spectral_mod_percentile, spectral_mod_multiplier, affect_uncond, dyn_cfg_augmentation = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 21, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_multidiffusion/scripts/forge_multidiffusion.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_multidiffusion/scripts/forge_multidiffusion.py", line 36, in process_before_every_sampling
enabled, method, tile_width, tile_height, tile_overlap, tile_batch_size = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 6, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_perturbed_attention/scripts/forge_perturbed_attention.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_perturbed_attention/scripts/forge_perturbed_attention.py", line 50, in process_before_every_sampling
enabled, scale, attenuation, start_step, end_step = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 5, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_sag/scripts/forge_sag.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_sag/scripts/forge_sag.py", line 197, in process_before_every_sampling
enabled, scale, blur_sigma, threshold = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 4, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_stylealign/scripts/forge_stylealign.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_stylealign/scripts/forge_stylealign.py", line 33, in process_before_every_sampling
shared_attention, strength = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 2, got 0)
---
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 7502.50 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 7502.50 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 1581.46 MB, All loaded to GPU.
Moving model(s) has taken 3.08 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
4%|▍ | 1/24 [00:00<00:09, 2.40it/s]
8%|▊ | 2/24 [00:00<00:06, 3.50it/s]
Total progress: 12%|█▎ | 3/24 [00:00<00:02, 10.45it/s][A
12%|█▎ | 3/24 [00:00<00:05, 4.07it/s]
17%|█▋ | 4/24 [00:01<00:04, 4.40it/s]
Total progress: 21%|██ | 5/24 [00:00<00:02, 6.84it/s][A
21%|██ | 5/24 [00:01<00:04, 4.60it/s]
Total progress: 25%|██▌ | 6/24 [00:00<00:02, 6.24it/s][A
25%|██▌ | 6/24 [00:01<00:03, 4.73it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:02, 5.85it/s][A
29%|██▉ | 7/24 [00:01<00:03, 4.81it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:02, 5.58it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.87it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.40it/s][A
38%|███▊ | 9/24 [00:02<00:03, 4.90it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.27it/s][A
42%|████▏ | 10/24 [00:02<00:02, 4.93it/s]
Total progress: 46%|████▌ | 11/24 [00:01<00:02, 5.19it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.96it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 5.14it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.98it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 5.10it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.99it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:01, 5.08it/s][A
58%|█████▊ | 14/24 [00:03<00:01, 5.01it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 5.07it/s][A
62%|██████▎ | 15/24 [00:03<00:01, 5.00it/s]
Total progress: 67%|██████▋ | 16/24 [00:02<00:01, 5.04it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 5.00it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 5.03it/s][A
71%|███████ | 17/24 [00:03<00:01, 5.00it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 5.02it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 5.01it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:00, 5.02it/s][A
79%|███████▉ | 19/24 [00:04<00:01, 5.00it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 5.01it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 4.99it/s]
Total progress: 88%|████████▊ | 21/24 [00:03<00:00, 5.00it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 4.99it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 5.00it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 5.00it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 5.00it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.99it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 5.00it/s][A
100%|██████████| 24/24 [00:05<00:00, 4.99it/s]
100%|██████████| 24/24 [00:05<00:00, 4.79it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 2484.88 MB ... Unload model JointTextEncoder Current free memory is 4245.24 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 4245.24 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3061.68 MB, All loaded to GPU.
Moving model(s) has taken 0.79 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 5.00it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.22it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4076.19 MB ... Unload model KModel Current free memory is 9073.53 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 9234.72 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 6457.74 MB, All loaded to GPU.
Moving model(s) has taken 0.60 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 7475.25 MB ... Done.
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 7474.50 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 7474.50 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 1553.45 MB, All loaded to GPU.
Moving model(s) has taken 1.66 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
Total progress: 8%|▊ | 2/24 [00:00<00:02, 10.22it/s][A
8%|▊ | 2/24 [00:00<00:04, 5.18it/s]
12%|█▎ | 3/24 [00:00<00:04, 5.10it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 6.32it/s][A
17%|█▋ | 4/24 [00:00<00:03, 5.06it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.86it/s][A
21%|██ | 5/24 [00:00<00:03, 5.04it/s]
Total progress: 25%|██▌ | 6/24 [00:00<00:03, 5.58it/s][A
25%|██▌ | 6/24 [00:01<00:03, 5.03it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.39it/s][A
29%|██▉ | 7/24 [00:01<00:03, 5.01it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.26it/s][A
33%|███▎ | 8/24 [00:01<00:03, 5.00it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.17it/s][A
38%|███▊ | 9/24 [00:01<00:03, 4.99it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.10it/s][A
42%|████▏ | 10/24 [00:01<00:02, 4.98it/s]
Total progress: 46%|████▌ | 11/24 [00:02<00:02, 5.06it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.98it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 5.04it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.98it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 5.03it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.98it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:01, 5.01it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 4.98it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 5.01it/s][A
62%|██████▎ | 15/24 [00:02<00:01, 4.98it/s]
Total progress: 67%|██████▋ | 16/24 [00:03<00:01, 5.00it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.98it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 4.99it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.99it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 5.00it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.98it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 4.99it/s][A
79%|███████▉ | 19/24 [00:03<00:01, 4.99it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 4.99it/s][A
83%|████████▎ | 20/24 [00:03<00:00, 4.99it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 4.99it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 4.98it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 4.98it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.99it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.99it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 5.00it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 5.00it/s][A
100%|██████████| 24/24 [00:04<00:00, 5.02it/s]
100%|██████████| 24/24 [00:04<00:00, 5.00it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 2475.34 MB ... Unload model JointTextEncoder Current free memory is 4234.19 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 4234.19 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3050.64 MB, All loaded to GPU.
Moving model(s) has taken 0.67 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 5.00it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.26it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4071.26 MB ... Unload model KModel Current free memory is 9071.65 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 9234.72 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 6457.74 MB, All loaded to GPU.
Moving model(s) has taken 0.59 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 7475.25 MB ... Done.
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 7474.50 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 7474.50 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 1553.45 MB, All loaded to GPU.
Moving model(s) has taken 1.67 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
Total progress: 8%|▊ | 2/24 [00:00<00:02, 10.10it/s][A
8%|▊ | 2/24 [00:00<00:04, 5.18it/s]
12%|█▎ | 3/24 [00:00<00:04, 5.11it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 6.32it/s][A
17%|█▋ | 4/24 [00:00<00:03, 5.08it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.87it/s][A
21%|██ | 5/24 [00:00<00:03, 5.04it/s]
Total progress: 25%|██▌ | 6/24 [00:00<00:03, 5.58it/s][A
25%|██▌ | 6/24 [00:01<00:03, 5.03it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.38it/s][A
29%|██▉ | 7/24 [00:01<00:03, 5.00it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.24it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.99it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.16it/s][A
38%|███▊ | 9/24 [00:01<00:03, 5.00it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.12it/s][A
42%|████▏ | 10/24 [00:01<00:02, 5.00it/s]
Total progress: 46%|████▌ | 11/24 [00:02<00:02, 5.08it/s][A
46%|████▌ | 11/24 [00:02<00:02, 5.00it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 5.06it/s][A
50%|█████ | 12/24 [00:02<00:02, 5.00it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 5.04it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 5.00it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:01, 5.02it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 4.99it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 5.01it/s][A
62%|██████▎ | 15/24 [00:02<00:01, 4.99it/s]
Total progress: 67%|██████▋ | 16/24 [00:03<00:01, 5.01it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.99it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 5.00it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.99it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 5.00it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 5.00it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:00, 5.01it/s][A
79%|███████▉ | 19/24 [00:03<00:00, 5.01it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 5.01it/s][A
83%|████████▎ | 20/24 [00:03<00:00, 5.01it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 5.01it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 5.00it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 5.00it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.99it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.98it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.99it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.99it/s][A
100%|██████████| 24/24 [00:04<00:00, 5.00it/s]
100%|██████████| 24/24 [00:04<00:00, 5.01it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 2473.83 MB ... Unload model JointTextEncoder Current free memory is 4232.69 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 4232.69 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3049.13 MB, All loaded to GPU.
Moving model(s) has taken 0.67 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.99it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.26it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4069.76 MB ... Unload model KModel Current free memory is 9070.14 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 9233.21 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 6456.23 MB, All loaded to GPU.
Moving model(s) has taken 0.60 seconds
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 7473.60 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 7473.60 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 1552.55 MB, All loaded to GPU.
Moving model(s) has taken 1.68 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
Total progress: 8%|▊ | 2/24 [00:00<00:02, 9.94it/s][A
8%|▊ | 2/24 [00:00<00:04, 5.15it/s]
Total progress: 12%|█▎ | 3/24 [00:00<00:02, 7.08it/s][A
12%|█▎ | 3/24 [00:00<00:04, 5.07it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 6.11it/s][A
17%|█▋ | 4/24 [00:00<00:03, 5.06it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.69it/s][A
21%|██ | 5/24 [00:00<00:03, 5.03it/s]
Total progress: 25%|██▌ | 6/24 [00:00<00:03, 5.44it/s][A
25%|██▌ | 6/24 [00:01<00:03, 5.02it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.29it/s][A
29%|██▉ | 7/24 [00:01<00:03, 5.00it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.18it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.99it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.11it/s][A
38%|███▊ | 9/24 [00:01<00:03, 4.99it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.07it/s][A
42%|████▏ | 10/24 [00:01<00:02, 4.98it/s]
Total progress: 46%|████▌ | 11/24 [00:02<00:02, 5.04it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.97it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 5.00it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.99it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 5.01it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.98it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:01, 5.01it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 4.98it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 4.99it/s][A
62%|██████▎ | 15/24 [00:02<00:01, 4.98it/s]
Total progress: 67%|██████▋ | 16/24 [00:03<00:01, 4.98it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.97it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 4.97it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.96it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 4.96it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.97it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 4.97it/s][A
79%|███████▉ | 19/24 [00:03<00:01, 4.96it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 4.96it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 4.95it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 4.95it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 4.96it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 4.97it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.96it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.96it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.95it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.96it/s][A
100%|██████████| 24/24 [00:04<00:00, 4.95it/s]
100%|██████████| 24/24 [00:04<00:00, 4.98it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 2472.94 MB ... Unload model JointTextEncoder Current free memory is 4231.79 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 4231.79 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3048.24 MB, All loaded to GPU.
Moving model(s) has taken 0.67 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.96it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.24it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4068.86 MB ... Unload model KModel Current free memory is 9069.25 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 9232.32 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 6455.34 MB, All loaded to GPU.
Moving model(s) has taken 0.61 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 7472.85 MB ... Done.
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 7472.10 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 7472.10 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 1551.05 MB, All loaded to GPU.
Moving model(s) has taken 1.67 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
Total progress: 8%|▊ | 2/24 [00:00<00:02, 10.04it/s][A
8%|▊ | 2/24 [00:00<00:04, 5.11it/s]
12%|█▎ | 3/24 [00:00<00:04, 5.07it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 6.30it/s][A
17%|█▋ | 4/24 [00:00<00:03, 5.04it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.85it/s][A
21%|██ | 5/24 [00:00<00:03, 5.02it/s]
Total progress: 25%|██▌ | 6/24 [00:01<00:03, 5.56it/s][A
25%|██▌ | 6/24 [00:01<00:03, 5.03it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.39it/s][A
29%|██▉ | 7/24 [00:01<00:03, 5.01it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.26it/s][A
33%|███▎ | 8/24 [00:01<00:03, 5.01it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.18it/s][A
38%|███▊ | 9/24 [00:01<00:03, 5.00it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.13it/s][A
42%|████▏ | 10/24 [00:01<00:02, 5.01it/s]
Total progress: 46%|████▌ | 11/24 [00:01<00:02, 5.09it/s][A
46%|████▌ | 11/24 [00:02<00:02, 5.00it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 5.06it/s][A
50%|█████ | 12/24 [00:02<00:02, 5.01it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 5.05it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.99it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:01, 5.02it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 5.00it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 5.02it/s][A
62%|██████▎ | 15/24 [00:02<00:01, 5.00it/s]
Total progress: 67%|██████▋ | 16/24 [00:02<00:01, 5.02it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 5.00it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 5.01it/s][A
71%|███████ | 17/24 [00:03<00:01, 5.01it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 5.01it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.99it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 5.00it/s][A
79%|███████▉ | 19/24 [00:03<00:01, 4.99it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 5.00it/s][A
83%|████████▎ | 20/24 [00:03<00:00, 4.99it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 5.00it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 4.99it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 4.99it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.99it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.99it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.99it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.98it/s][A
100%|██████████| 24/24 [00:04<00:00, 4.99it/s]
100%|██████████| 24/24 [00:04<00:00, 5.01it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 2473.83 MB ... Unload model JointTextEncoder Current free memory is 4232.69 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 4232.69 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3049.13 MB, All loaded to GPU.
Moving model(s) has taken 0.68 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.98it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.26it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4069.76 MB ... Unload model KModel Current free memory is 9070.14 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 9233.21 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 6456.23 MB, All loaded to GPU.
Moving model(s) has taken 0.60 seconds
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 7473.60 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 7473.60 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 1552.55 MB, All loaded to GPU.
Moving model(s) has taken 1.67 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
Total progress: 8%|▊ | 2/24 [00:00<00:02, 9.94it/s][A
8%|▊ | 2/24 [00:00<00:04, 5.14it/s]
Total progress: 12%|█▎ | 3/24 [00:00<00:02, 7.06it/s][A
12%|█▎ | 3/24 [00:00<00:04, 5.05it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 6.09it/s][A
17%|█▋ | 4/24 [00:00<00:03, 5.03it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.66it/s][A
21%|██ | 5/24 [00:00<00:03, 5.03it/s]
Total progress: 25%|██▌ | 6/24 [00:01<00:03, 5.44it/s][A
25%|██▌ | 6/24 [00:01<00:03, 5.02it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.29it/s][A
29%|██▉ | 7/24 [00:01<00:03, 5.01it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.18it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.99it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.11it/s][A
38%|███▊ | 9/24 [00:01<00:03, 4.99it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.07it/s][A
42%|████▏ | 10/24 [00:01<00:02, 4.97it/s]
Total progress: 46%|████▌ | 11/24 [00:02<00:02, 5.04it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.98it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 5.02it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.97it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 5.00it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.98it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:02, 4.99it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 4.97it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 4.98it/s][A
62%|██████▎ | 15/24 [00:03<00:01, 4.96it/s]
Total progress: 67%|██████▋ | 16/24 [00:03<00:01, 4.97it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.96it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 4.97it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.96it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 4.96it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.96it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 4.95it/s][A
79%|███████▉ | 19/24 [00:03<00:01, 4.97it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 4.98it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 4.99it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 4.99it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 4.98it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 4.98it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.97it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.97it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.97it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.97it/s][A
100%|██████████| 24/24 [00:04<00:00, 4.99it/s]
100%|██████████| 24/24 [00:04<00:00, 4.99it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 2472.94 MB ... Unload model JointTextEncoder Current free memory is 4231.79 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 4231.79 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3048.24 MB, All loaded to GPU.
Moving model(s) has taken 0.67 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.97it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.25it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4068.86 MB ... Unload model KModel Current free memory is 9069.25 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 9232.32 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 6455.34 MB, All loaded to GPU.
Moving model(s) has taken 0.66 seconds
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 7472.71 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 7472.71 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 1551.66 MB, All loaded to GPU.
Moving model(s) has taken 1.86 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
Total progress: 8%|▊ | 2/24 [00:00<00:02, 9.85it/s][A
8%|▊ | 2/24 [00:00<00:04, 5.09it/s]
Total progress: 12%|█▎ | 3/24 [00:00<00:02, 7.03it/s][A
12%|█▎ | 3/24 [00:00<00:04, 5.05it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 6.09it/s][A
17%|█▋ | 4/24 [00:00<00:03, 5.01it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.64it/s][A
21%|██ | 5/24 [00:00<00:03, 5.00it/s]
Total progress: 25%|██▌ | 6/24 [00:01<00:03, 5.40it/s][A
25%|██▌ | 6/24 [00:01<00:03, 4.99it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.26it/s][A
29%|██▉ | 7/24 [00:01<00:03, 4.98it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.16it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.98it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.09it/s][A
38%|███▊ | 9/24 [00:01<00:03, 4.95it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.03it/s][A
42%|████▏ | 10/24 [00:02<00:02, 4.95it/s]
Total progress: 46%|████▌ | 11/24 [00:02<00:02, 5.01it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.95it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 5.00it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.96it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 4.98it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.94it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:02, 4.95it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 4.92it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 4.94it/s][A
62%|██████▎ | 15/24 [00:03<00:01, 4.93it/s]
Total progress: 67%|██████▋ | 16/24 [00:03<00:01, 4.94it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.92it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 4.93it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.93it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 4.94it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.92it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 4.92it/s][A
79%|███████▉ | 19/24 [00:03<00:01, 4.91it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 4.91it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 4.91it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 4.91it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 4.90it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 4.90it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.90it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.90it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.89it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.90it/s][A
100%|██████████| 24/24 [00:04<00:00, 4.90it/s]
100%|██████████| 24/24 [00:04<00:00, 4.94it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 2472.04 MB ... Unload model JointTextEncoder Current free memory is 4230.90 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 4230.90 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3047.34 MB, All loaded to GPU.
Moving model(s) has taken 0.73 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.90it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.15it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4067.97 MB ... Unload model KModel Current free memory is 9068.36 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 9231.42 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 6454.45 MB, All loaded to GPU.
Moving model(s) has taken 0.68 seconds
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 7471.81 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 7471.81 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 1550.77 MB, All loaded to GPU.
Moving model(s) has taken 2.15 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
4%|▍ | 1/24 [00:00<00:03, 7.07it/s]
Total progress: 8%|▊ | 2/24 [00:00<00:02, 10.53it/s][A
8%|▊ | 2/24 [00:00<00:04, 4.82it/s]
12%|█▎ | 3/24 [00:00<00:04, 4.87it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 6.15it/s][A
17%|█▋ | 4/24 [00:00<00:04, 4.89it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.86it/s][A
21%|██ | 5/24 [00:01<00:03, 4.89it/s]
Total progress: 25%|██▌ | 6/24 [00:01<00:03, 5.52it/s][A
25%|██▌ | 6/24 [00:01<00:03, 4.90it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.37it/s][A
29%|██▉ | 7/24 [00:01<00:03, 4.92it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.22it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.92it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.08it/s][A
38%|███▊ | 9/24 [00:01<00:03, 4.92it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.05it/s][A
42%|████▏ | 10/24 [00:02<00:02, 4.91it/s]
Total progress: 46%|████▌ | 11/24 [00:02<00:02, 5.01it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.90it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 4.95it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.89it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 4.93it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.89it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:02, 4.92it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 4.89it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 4.96it/s][A
62%|██████▎ | 15/24 [00:03<00:01, 4.88it/s]
Total progress: 67%|██████▋ | 16/24 [00:03<00:01, 4.92it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.87it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 4.88it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.87it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 4.09it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.41it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 3.88it/s][A
79%|███████▉ | 19/24 [00:04<00:01, 4.05it/s]
Total progress: 83%|████████▎ | 20/24 [00:04<00:01, 3.92it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 4.04it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 3.86it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 3.95it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 3.84it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 3.90it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 3.80it/s][A
96%|█████████▌| 23/24 [00:05<00:00, 3.86it/s]
Total progress: 100%|██████████| 24/24 [00:05<00:00, 3.52it/s][A
100%|██████████| 24/24 [00:05<00:00, 3.55it/s]
100%|██████████| 24/24 [00:05<00:00, 4.44it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 2471.15 MB ... Unload model JointTextEncoder Current free memory is 4230.00 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 4230.00 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3046.45 MB, All loaded to GPU.
Moving model(s) has taken 1.17 seconds
Total progress: 100%|██████████| 24/24 [00:06<00:00, 3.52it/s][A
Total progress: 100%|██████████| 24/24 [00:06<00:00, 3.54it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4067.08 MB ... Unload model KModel Current free memory is 9067.46 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 9230.53 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 6453.55 MB, All loaded to GPU.
Moving model(s) has taken 1.30 seconds
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 7470.92 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 7470.92 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 1549.87 MB, All loaded to GPU.
Moving model(s) has taken 2.29 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
4%|▍ | 1/24 [00:00<00:03, 7.49it/s]
Total progress: 8%|▊ | 2/24 [00:00<00:02, 10.35it/s][A
8%|▊ | 2/24 [00:00<00:04, 4.79it/s]
12%|█▎ | 3/24 [00:00<00:04, 4.88it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 6.40it/s][A
17%|█▋ | 4/24 [00:00<00:04, 4.91it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.83it/s][A
21%|██ | 5/24 [00:01<00:03, 4.88it/s]
Total progress: 25%|██▌ | 6/24 [00:01<00:03, 5.51it/s][A
25%|██▌ | 6/24 [00:01<00:03, 4.89it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.24it/s][A
29%|██▉ | 7/24 [00:01<00:03, 4.91it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.11it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.88it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.12it/s][A
38%|███▊ | 9/24 [00:01<00:03, 4.89it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.04it/s][A
42%|████▏ | 10/24 [00:02<00:02, 4.92it/s]
Total progress: 46%|████▌ | 11/24 [00:02<00:02, 5.05it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.90it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 4.95it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.88it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 4.92it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.84it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:02, 4.91it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 4.85it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 4.88it/s][A
62%|██████▎ | 15/24 [00:03<00:01, 4.86it/s]
Total progress: 67%|██████▋ | 16/24 [00:03<00:01, 4.88it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.85it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 4.86it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.84it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 4.87it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.85it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 4.86it/s][A
79%|███████▉ | 19/24 [00:03<00:01, 4.84it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 4.80it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 4.84it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 4.82it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 4.84it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 4.85it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.85it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.89it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.86it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.88it/s][A
100%|██████████| 24/24 [00:04<00:00, 4.86it/s]
100%|██████████| 24/24 [00:04<00:00, 4.89it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 2472.94 MB ... Unload model JointTextEncoder Current free memory is 4231.79 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 4231.79 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3048.24 MB, All loaded to GPU.
Moving model(s) has taken 0.88 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.88it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.04it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4068.86 MB ... Unload model KModel Current free memory is 9069.25 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 9232.32 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 6455.34 MB, All loaded to GPU.
Moving model(s) has taken 0.69 seconds
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 7472.71 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 7472.71 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 1551.66 MB, All loaded to GPU.
Moving model(s) has taken 2.01 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
4%|▍ | 1/24 [00:00<00:02, 9.13it/s]
Total progress: 8%|▊ | 2/24 [00:00<00:01, 11.55it/s][A
8%|▊ | 2/24 [00:00<00:04, 4.76it/s]
12%|█▎ | 3/24 [00:00<00:04, 4.84it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 6.49it/s][A
17%|█▋ | 4/24 [00:00<00:04, 4.88it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.79it/s][A
21%|██ | 5/24 [00:01<00:03, 4.87it/s]
Total progress: 25%|██▌ | 6/24 [00:00<00:03, 5.61it/s][A
25%|██▌ | 6/24 [00:01<00:03, 4.90it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.35it/s][A
29%|██▉ | 7/24 [00:01<00:03, 4.90it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.12it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.90it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.06it/s][A
38%|███▊ | 9/24 [00:01<00:03, 4.90it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.01it/s][A
42%|████▏ | 10/24 [00:02<00:02, 4.90it/s]
Total progress: 46%|████▌ | 11/24 [00:02<00:02, 4.95it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.90it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 4.94it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.89it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 4.96it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.88it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:02, 4.61it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 4.86it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 4.56it/s][A
62%|██████▎ | 15/24 [00:03<00:01, 4.87it/s]
Total progress: 67%|██████▋ | 16/24 [00:03<00:01, 4.87it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.88it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 4.99it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.89it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 5.03it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.90it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 4.87it/s][A
79%|███████▉ | 19/24 [00:03<00:01, 4.90it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 4.82it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 4.90it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 5.16it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 4.90it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 4.87it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.92it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.98it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.90it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.97it/s][A
100%|██████████| 24/24 [00:04<00:00, 4.89it/s]
100%|██████████| 24/24 [00:04<00:00, 4.92it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 2472.04 MB ... Unload model JointTextEncoder Current free memory is 4230.90 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 4230.90 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3047.34 MB, All loaded to GPU.
Moving model(s) has taken 0.77 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.97it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.12it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4067.97 MB ... Unload model KModel Current free memory is 9068.36 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 9231.42 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 6454.45 MB, All loaded to GPU.
Moving model(s) has taken 0.69 seconds
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 7471.81 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 7471.81 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 1550.77 MB, All loaded to GPU.
Moving model(s) has taken 1.88 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
Total progress: 8%|▊ | 2/24 [00:00<00:02, 9.86it/s][A
8%|▊ | 2/24 [00:00<00:04, 5.03it/s]
Total progress: 12%|█▎ | 3/24 [00:00<00:03, 6.97it/s][A
12%|█▎ | 3/24 [00:00<00:04, 4.98it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 6.02it/s][A
17%|█▋ | 4/24 [00:00<00:04, 4.96it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.59it/s][A
21%|██ | 5/24 [00:01<00:03, 4.95it/s]
Total progress: 25%|██▌ | 6/24 [00:01<00:03, 5.36it/s][A
25%|██▌ | 6/24 [00:01<00:03, 4.95it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.22it/s][A
29%|██▉ | 7/24 [00:01<00:03, 4.94it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.12it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.93it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.05it/s][A
38%|███▊ | 9/24 [00:01<00:03, 4.92it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.00it/s][A
42%|████▏ | 10/24 [00:02<00:02, 4.91it/s]
Total progress: 46%|████▌ | 11/24 [00:02<00:02, 4.97it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.91it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 4.95it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.90it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 4.93it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.90it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:02, 4.91it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 4.89it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 4.90it/s][A
62%|██████▎ | 15/24 [00:03<00:01, 4.89it/s]
Total progress: 67%|██████▋ | 16/24 [00:03<00:01, 4.91it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.91it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 4.92it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.93it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 4.93it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.94it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 4.94it/s][A
79%|███████▉ | 19/24 [00:03<00:01, 4.94it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 4.95it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 4.94it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 4.95it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 4.93it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 4.93it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.92it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.91it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.92it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.92it/s][A
100%|██████████| 24/24 [00:04<00:00, 4.91it/s]
100%|██████████| 24/24 [00:04<00:00, 4.93it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 2471.15 MB ... Unload model JointTextEncoder Current free memory is 4230.00 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 4230.00 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3046.45 MB, All loaded to GPU.
Moving model(s) has taken 0.72 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.92it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.15it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4067.08 MB ... Unload model KModel Current free memory is 9067.46 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 9230.53 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 6453.55 MB, All loaded to GPU.
Moving model(s) has taken 0.66 seconds
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 7470.92 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 7470.92 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 1549.87 MB, All loaded to GPU.
Moving model(s) has taken 1.95 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
Total progress: 8%|▊ | 2/24 [00:00<00:02, 9.33it/s][A
8%|▊ | 2/24 [00:00<00:04, 5.03it/s]
Total progress: 12%|█▎ | 3/24 [00:00<00:03, 6.66it/s][A
12%|█▎ | 3/24 [00:00<00:04, 5.00it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 6.30it/s][A
17%|█▋ | 4/24 [00:00<00:04, 4.99it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.47it/s][A
21%|██ | 5/24 [00:01<00:03, 4.95it/s]
Total progress: 25%|██▌ | 6/24 [00:01<00:03, 5.31it/s][A
25%|██▌ | 6/24 [00:01<00:03, 4.93it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.29it/s][A
29%|██▉ | 7/24 [00:01<00:03, 4.92it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.10it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.90it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:03, 4.98it/s][A
38%|███▊ | 9/24 [00:01<00:03, 4.89it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 4.79it/s][A
42%|████▏ | 10/24 [00:02<00:02, 4.87it/s]
Total progress: 46%|████▌ | 11/24 [00:02<00:02, 4.83it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.86it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 5.09it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.86it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 4.94it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.86it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:02, 4.82it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 4.84it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 4.83it/s][A
62%|██████▎ | 15/24 [00:03<00:01, 4.85it/s]
Total progress: 67%|██████▋ | 16/24 [00:03<00:01, 4.88it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.87it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 5.01it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.88it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 5.00it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.89it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 4.98it/s][A
79%|███████▉ | 19/24 [00:03<00:01, 4.90it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 4.76it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 4.89it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 4.90it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 4.88it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 4.90it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.87it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.91it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.87it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.94it/s][A
100%|██████████| 24/24 [00:04<00:00, 4.85it/s]
100%|██████████| 24/24 [00:04<00:00, 4.89it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 2470.25 MB ... Unload model JointTextEncoder Current free memory is 4229.11 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 4229.11 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3045.55 MB, All loaded to GPU.
Moving model(s) has taken 0.76 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.94it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.11it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4066.18 MB ... Unload model KModel Current free memory is 9066.57 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 9229.64 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 6452.66 MB, All loaded to GPU.
Moving model(s) has taken 0.61 seconds
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 7470.03 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 7470.03 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 1548.98 MB, All loaded to GPU.
Moving model(s) has taken 1.67 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
Total progress: 8%|▊ | 2/24 [00:00<00:02, 9.98it/s][A
8%|▊ | 2/24 [00:00<00:04, 5.12it/s]
Total progress: 12%|█▎ | 3/24 [00:00<00:02, 7.06it/s][A
12%|█▎ | 3/24 [00:00<00:04, 5.09it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 6.13it/s][A
17%|█▋ | 4/24 [00:00<00:03, 5.04it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.67it/s][A
21%|██ | 5/24 [00:00<00:03, 5.01it/s]
Total progress: 25%|██▌ | 6/24 [00:01<00:03, 5.42it/s][A
25%|██▌ | 6/24 [00:01<00:03, 5.00it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.26it/s][A
29%|██▉ | 7/24 [00:01<00:03, 4.98it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.15it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.99it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.12it/s][A
38%|███▊ | 9/24 [00:01<00:03, 4.98it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.07it/s][A
42%|████▏ | 10/24 [00:01<00:02, 4.97it/s]
Total progress: 46%|████▌ | 11/24 [00:02<00:02, 5.03it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.97it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 5.01it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.96it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 4.99it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.95it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:02, 4.97it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 4.98it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 4.99it/s][A
62%|██████▎ | 15/24 [00:03<00:01, 4.98it/s]
Total progress: 67%|██████▋ | 16/24 [00:03<00:01, 4.99it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.97it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 4.98it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.97it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 4.97it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.96it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 4.96it/s][A
79%|███████▉ | 19/24 [00:03<00:01, 4.96it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 4.96it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 4.95it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 4.95it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 4.95it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 4.96it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.95it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.95it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.94it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.94it/s][A
100%|██████████| 24/24 [00:04<00:00, 4.93it/s]
100%|██████████| 24/24 [00:04<00:00, 4.97it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 2472.04 MB ... Unload model JointTextEncoder Current free memory is 4230.90 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 4230.90 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3047.34 MB, All loaded to GPU.
Moving model(s) has taken 0.67 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.94it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.24it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4067.97 MB ... Unload model KModel Current free memory is 9068.36 MB ... Unload model IntegratedAutoencoderKL Done.
################################################################
[1m[32mInstall script for stable-diffusion + Web UI
[1m[34mTested on Debian 11 (Bullseye), Fedora 34+ and openSUSE Leap 15.4 or newer.[0m
################################################################
################################################################
Running on [1m[32mroot[0m user
################################################################
################################################################
Repo already cloned, using it as install directory
################################################################
################################################################
Create and activate python venv
################################################################
################################################################
Launching launch.py...
################################################################
glibc version is 2.39
Check TCMalloc: libtcmalloc_minimal.so.4
libtcmalloc_minimal.so.4 is linked with libc.so,execute LD_PRELOAD=/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4
=============================================================================================
INCOMPATIBLE PYTHON VERSION
This program is tested with 3.10.6 Python, but you have 3.12.3.
If you encounter an error with "RuntimeError: Couldn't install torch." message,
or any other error regarding unsuccessful package (library) installation,
please downgrade (or upgrade) to the latest version of 3.10 Python
and delete current Python and "venv" folder in WebUI's directory.
You can download 3.10 Python from here: https://www.python.org/downloads/release/python-3106/
Use --skip-python-version-check to suppress this warning.
=============================================================================================
Python 3.12.3 (main, Jan 22 2026, 20:57:42) [GCC 13.3.0]
Version: f2.0.1v1.10.1-previous-669-gdfdcbab6
Commit hash: dfdcbab685e57677014f05a3309b48cc87383167
Legacy Preprocessor init warning: Unable to install insightface automatically. Please try run `pip install insightface` manually.
Launching Web UI with arguments: -f --listen --api --enable-insecure-extension-access --xformers --no-half-vae --port 7887
Total VRAM 20017 MB, total RAM 64105 MB
pytorch version: 2.3.1+cu121
WARNING:xformers:A matching Triton is not available, some optimizations will not be enabled
Traceback (most recent call last):
File "/opt/sd-webui/venv/lib/python3.12/site-packages/xformers/__init__.py", line 57, in _is_triton_available
import triton # noqa
^^^^^^^^^^^^^
ModuleNotFoundError: No module named 'triton'
xformers version: 0.0.27
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA RTX 4000 SFF Ada Generation : native
Hint: your device supports --cuda-malloc for potential speed improvements.
VAE dtype preferences: [torch.bfloat16, torch.float32] -> torch.bfloat16
CUDA Using Stream: False
Using xformers cross attention
Using xformers attention for VAE
ControlNet preprocessor location: /opt/sd-webui/models/ControlNetPreprocessor
*** Error loading script: soft_inpainting.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 525, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/sd-webui/modules/script_loading.py", line 13, in load_module
module_spec.loader.exec_module(module)
File "<frozen importlib._bootstrap_external>", line 995, in exec_module
File "<frozen importlib._bootstrap>", line 488, in _call_with_frames_removed
File "/opt/sd-webui/extensions-builtin/soft-inpainting/scripts/soft_inpainting.py", line 10, in <module>
from joblib import Parallel, delayed, cpu_count
ModuleNotFoundError: No module named 'joblib'
---
2026-02-26 11:28:39,968 - ControlNet - [0;32mINFO[0m - ControlNet UI callback registered.
Model selected: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
Using online LoRAs in FP16: False
Running on local URL: http://0.0.0.0:7887
To create a public link, set `share=True` in `launch()`.
Loading Model: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Done.
Startup time: 7.3s (prepare environment: 1.1s, launcher: 0.2s, import torch: 2.8s, load scripts: 0.7s, create ui: 1.1s, gradio launch: 0.5s, add APIs: 0.8s).
StateDict Keys: {'unet': 1680, 'vae': 248, 'text_encoder': 197, 'text_encoder_2': 518, 'ignore': 0}
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
K-Model Created: {'storage_dtype': torch.float16, 'computation_dtype': torch.float16}
Model loaded in 0.6s (unload existing model: 0.1s, forge model load: 0.5s).
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3051.58 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 9306.96 MB, Model Require: 1559.68 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 6723.28 MB, All loaded to GPU.
Moving model(s) has taken 0.55 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 7503.26 MB ... Done.
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 7502.50 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 7502.50 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 1581.46 MB, All loaded to GPU.
Moving model(s) has taken 1.85 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
4%|▍ | 1/24 [00:00<00:06, 3.58it/s]
8%|▊ | 2/24 [00:00<00:05, 4.35it/s]
Total progress: 12%|█▎ | 3/24 [00:00<00:02, 10.43it/s][A
12%|█▎ | 3/24 [00:00<00:04, 4.65it/s]
17%|█▋ | 4/24 [00:00<00:04, 4.78it/s]
Total progress: 21%|██ | 5/24 [00:00<00:02, 6.83it/s][A
21%|██ | 5/24 [00:01<00:03, 4.86it/s]
Total progress: 25%|██▌ | 6/24 [00:00<00:02, 6.25it/s][A
25%|██▌ | 6/24 [00:01<00:03, 4.91it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:02, 5.85it/s][A
29%|██▉ | 7/24 [00:01<00:03, 4.94it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:02, 5.59it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.96it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.41it/s][A
38%|███▊ | 9/24 [00:01<00:03, 4.97it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.28it/s][A
42%|████▏ | 10/24 [00:02<00:02, 4.98it/s]
Total progress: 46%|████▌ | 11/24 [00:01<00:02, 5.20it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.98it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 5.13it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.98it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 5.09it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.98it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:01, 5.06it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 4.98it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 5.03it/s][A
62%|██████▎ | 15/24 [00:03<00:01, 4.99it/s]
Total progress: 67%|██████▋ | 16/24 [00:02<00:01, 5.03it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.99it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 5.01it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.99it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 5.01it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.98it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 5.00it/s][A
79%|███████▉ | 19/24 [00:03<00:01, 4.99it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 5.00it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 4.99it/s]
Total progress: 88%|████████▊ | 21/24 [00:03<00:00, 5.00it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 5.00it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 5.00it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.99it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 5.00it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 5.00it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 5.00it/s][A
100%|██████████| 24/24 [00:04<00:00, 5.00it/s]
100%|██████████| 24/24 [00:04<00:00, 4.92it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 2484.88 MB ... Unload model JointTextEncoder Current free memory is 4245.24 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 4245.24 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3061.68 MB, All loaded to GPU.
Moving model(s) has taken 0.75 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 5.00it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.26it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4076.19 MB ... Unload model KModel Current free memory is 9073.53 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 9234.72 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 6457.74 MB, All loaded to GPU.
Moving model(s) has taken 0.61 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 7475.25 MB ... Done.
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 7474.50 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 7474.50 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 1553.45 MB, All loaded to GPU.
Moving model(s) has taken 1.71 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
Total progress: 8%|▊ | 2/24 [00:00<00:02, 9.99it/s][A
8%|▊ | 2/24 [00:00<00:04, 5.24it/s]
Total progress: 12%|█▎ | 3/24 [00:00<00:02, 7.06it/s][A
12%|█▎ | 3/24 [00:00<00:04, 5.13it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 6.11it/s][A
17%|█▋ | 4/24 [00:00<00:03, 5.07it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.66it/s][A
21%|██ | 5/24 [00:00<00:03, 5.05it/s]
Total progress: 25%|██▌ | 6/24 [00:01<00:03, 5.43it/s][A
25%|██▌ | 6/24 [00:01<00:03, 5.03it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.27it/s][A
29%|██▉ | 7/24 [00:01<00:03, 5.03it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.19it/s][A
33%|███▎ | 8/24 [00:01<00:03, 5.00it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.12it/s][A
38%|███▊ | 9/24 [00:01<00:02, 5.01it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.08it/s][A
42%|████▏ | 10/24 [00:01<00:02, 5.00it/s]
Total progress: 46%|████▌ | 11/24 [00:02<00:02, 5.06it/s][A
46%|████▌ | 11/24 [00:02<00:02, 5.01it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 5.04it/s][A
50%|█████ | 12/24 [00:02<00:02, 5.00it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 5.03it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 5.01it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:01, 5.02it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 4.99it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 5.01it/s][A
62%|██████▎ | 15/24 [00:02<00:01, 5.00it/s]
Total progress: 67%|██████▋ | 16/24 [00:03<00:01, 5.01it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 5.00it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 5.01it/s][A
71%|███████ | 17/24 [00:03<00:01, 5.00it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 5.01it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 5.00it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:00, 5.01it/s][A
79%|███████▉ | 19/24 [00:03<00:00, 5.03it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 5.03it/s][A
83%|████████▎ | 20/24 [00:03<00:00, 5.02it/s]
Total progress: 88%|████████▊ | 21/24 [00:03<00:00, 5.02it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 5.02it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 5.03it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 5.03it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 5.03it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 5.03it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 5.03it/s][A
100%|██████████| 24/24 [00:04<00:00, 5.04it/s]
100%|██████████| 24/24 [00:04<00:00, 5.03it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 2475.34 MB ... Unload model JointTextEncoder Current free memory is 4234.19 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 4234.19 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3050.64 MB, All loaded to GPU.
Moving model(s) has taken 0.68 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 5.03it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.26it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4071.26 MB ... Unload model KModel Current free memory is 9071.65 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 9234.72 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 6457.74 MB, All loaded to GPU.
Moving model(s) has taken 0.60 seconds
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 7475.11 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 7475.11 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 1554.06 MB, All loaded to GPU.
Moving model(s) has taken 1.69 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
Total progress: 8%|▊ | 2/24 [00:00<00:02, 10.00it/s][A
8%|▊ | 2/24 [00:00<00:04, 5.15it/s]
Total progress: 12%|█▎ | 3/24 [00:00<00:02, 7.09it/s][A
12%|█▎ | 3/24 [00:00<00:04, 5.08it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 6.14it/s][A
17%|█▋ | 4/24 [00:00<00:03, 5.06it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.70it/s][A
21%|██ | 5/24 [00:00<00:03, 5.07it/s]
Total progress: 25%|██▌ | 6/24 [00:00<00:03, 5.48it/s][A
25%|██▌ | 6/24 [00:01<00:03, 5.05it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.32it/s][A
29%|██▉ | 7/24 [00:01<00:03, 5.04it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.22it/s][A
33%|███▎ | 8/24 [00:01<00:03, 5.03it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.15it/s][A
38%|███▊ | 9/24 [00:01<00:02, 5.01it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.09it/s][A
42%|████▏ | 10/24 [00:01<00:02, 4.99it/s]
Total progress: 46%|████▌ | 11/24 [00:01<00:02, 5.05it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.99it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 5.03it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.98it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 5.02it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.98it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:01, 5.00it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 4.97it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 4.99it/s][A
62%|██████▎ | 15/24 [00:02<00:01, 4.98it/s]
Total progress: 67%|██████▋ | 16/24 [00:03<00:01, 4.98it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.97it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 4.98it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.96it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 4.97it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.97it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 4.97it/s][A
79%|███████▉ | 19/24 [00:03<00:01, 4.98it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 4.98it/s][A
83%|████████▎ | 20/24 [00:03<00:00, 4.97it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 4.97it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 4.96it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 4.96it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.97it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.96it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.96it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.96it/s][A
100%|██████████| 24/24 [00:04<00:00, 4.95it/s]
100%|██████████| 24/24 [00:04<00:00, 4.99it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 2474.44 MB ... Unload model JointTextEncoder Current free memory is 4233.30 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 4233.30 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3049.74 MB, All loaded to GPU.
Moving model(s) has taken 0.68 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.96it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.24it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4070.37 MB ... Unload model KModel Current free memory is 9070.76 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 9233.83 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 6456.85 MB, All loaded to GPU.
Moving model(s) has taken 0.61 seconds
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 7474.22 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 7474.22 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 1553.17 MB, All loaded to GPU.
Moving model(s) has taken 1.67 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
Total progress: 8%|▊ | 2/24 [00:00<00:02, 10.30it/s][A
8%|▊ | 2/24 [00:00<00:04, 5.37it/s]
12%|█▎ | 3/24 [00:00<00:04, 5.21it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 6.35it/s][A
17%|█▋ | 4/24 [00:00<00:03, 5.13it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.88it/s][A
21%|██ | 5/24 [00:00<00:03, 5.06it/s]
Total progress: 25%|██▌ | 6/24 [00:00<00:03, 5.57it/s][A
25%|██▌ | 6/24 [00:01<00:03, 5.04it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.39it/s][A
29%|██▉ | 7/24 [00:01<00:03, 5.03it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.27it/s][A
33%|███▎ | 8/24 [00:01<00:03, 5.02it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.18it/s][A
38%|███▊ | 9/24 [00:01<00:02, 5.00it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.11it/s][A
42%|████▏ | 10/24 [00:01<00:02, 4.99it/s]
Total progress: 46%|████▌ | 11/24 [00:01<00:02, 5.07it/s][A
46%|████▌ | 11/24 [00:02<00:02, 5.00it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 5.06it/s][A
50%|█████ | 12/24 [00:02<00:02, 5.00it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 5.03it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 5.00it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:01, 5.03it/s][A
58%|█████▊ | 14/24 [00:02<00:01, 5.01it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 5.03it/s][A
62%|██████▎ | 15/24 [00:02<00:01, 5.00it/s]
Total progress: 67%|██████▋ | 16/24 [00:02<00:01, 5.01it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 5.00it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 5.01it/s][A
71%|███████ | 17/24 [00:03<00:01, 5.00it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 4.99it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.98it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 4.98it/s][A
79%|███████▉ | 19/24 [00:03<00:01, 5.00it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 5.00it/s][A
83%|████████▎ | 20/24 [00:03<00:00, 5.00it/s]
Total progress: 88%|████████▊ | 21/24 [00:03<00:00, 5.00it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 5.00it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 5.00it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.99it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.99it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.99it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.99it/s][A
100%|██████████| 24/24 [00:04<00:00, 4.99it/s]
100%|██████████| 24/24 [00:04<00:00, 5.02it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 2473.55 MB ... Unload model JointTextEncoder Current free memory is 4232.40 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 4232.40 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3048.85 MB, All loaded to GPU.
Moving model(s) has taken 0.68 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.99it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.26it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4069.48 MB ... Unload model KModel Current free memory is 9069.86 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 9232.93 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 6455.95 MB, All loaded to GPU.
Moving model(s) has taken 0.59 seconds
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 7473.32 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 7473.32 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 1552.27 MB, All loaded to GPU.
Moving model(s) has taken 1.66 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
Total progress: 8%|▊ | 2/24 [00:00<00:02, 9.94it/s][A
8%|▊ | 2/24 [00:00<00:04, 5.14it/s]
Total progress: 12%|█▎ | 3/24 [00:00<00:02, 7.04it/s][A
12%|█▎ | 3/24 [00:00<00:04, 5.07it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 6.11it/s][A
17%|█▋ | 4/24 [00:00<00:03, 5.04it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.67it/s][A
21%|██ | 5/24 [00:00<00:03, 5.03it/s]
Total progress: 25%|██▌ | 6/24 [00:00<00:03, 5.45it/s][A
25%|██▌ | 6/24 [00:01<00:03, 5.04it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.30it/s][A
29%|██▉ | 7/24 [00:01<00:03, 5.02it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.20it/s][A
33%|███▎ | 8/24 [00:01<00:03, 5.02it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.14it/s][A
38%|███▊ | 9/24 [00:01<00:02, 5.02it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.11it/s][A
42%|████▏ | 10/24 [00:01<00:02, 5.02it/s]
Total progress: 46%|████▌ | 11/24 [00:01<00:02, 5.08it/s][A
46%|████▌ | 11/24 [00:02<00:02, 5.03it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 5.07it/s][A
50%|█████ | 12/24 [00:02<00:02, 5.03it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 5.06it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 5.01it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:01, 5.03it/s][A
58%|█████▊ | 14/24 [00:02<00:01, 5.01it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 5.02it/s][A
62%|██████▎ | 15/24 [00:02<00:01, 5.00it/s]
Total progress: 67%|██████▋ | 16/24 [00:02<00:01, 5.01it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 5.01it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 5.01it/s][A
71%|███████ | 17/24 [00:03<00:01, 5.00it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 5.01it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 5.00it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:00, 5.00it/s][A
79%|███████▉ | 19/24 [00:03<00:01, 5.00it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 5.00it/s][A
83%|████████▎ | 20/24 [00:03<00:00, 5.00it/s]
Total progress: 88%|████████▊ | 21/24 [00:03<00:00, 5.00it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 5.00it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 5.00it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 5.00it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 5.00it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 5.00it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 5.00it/s][A
100%|██████████| 24/24 [00:04<00:00, 5.00it/s]
100%|██████████| 24/24 [00:04<00:00, 5.02it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 2472.65 MB ... Unload model JointTextEncoder Current free memory is 4231.51 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 4231.51 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3047.95 MB, All loaded to GPU.
Moving model(s) has taken 0.67 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 5.00it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.26it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4068.58 MB ... Unload model KModel Current free memory is 9068.97 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 9234.11 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 6457.13 MB, All loaded to GPU.
Moving model(s) has taken 0.60 seconds
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 7475.11 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 7475.11 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 1554.06 MB, All loaded to GPU.
Moving model(s) has taken 1.67 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
Total progress: 8%|▊ | 2/24 [00:00<00:02, 10.04it/s][A
8%|▊ | 2/24 [00:00<00:04, 5.23it/s]
12%|█▎ | 3/24 [00:00<00:04, 5.12it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 6.27it/s][A
17%|█▋ | 4/24 [00:00<00:03, 5.05it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.82it/s][A
21%|██ | 5/24 [00:00<00:03, 5.03it/s]
Total progress: 25%|██▌ | 6/24 [00:01<00:03, 5.55it/s][A
25%|██▌ | 6/24 [00:01<00:03, 5.02it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.36it/s][A
29%|██▉ | 7/24 [00:01<00:03, 5.00it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.24it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.99it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.15it/s][A
38%|███▊ | 9/24 [00:01<00:03, 4.98it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.09it/s][A
42%|████▏ | 10/24 [00:01<00:02, 4.97it/s]
Total progress: 46%|████▌ | 11/24 [00:02<00:02, 5.05it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.96it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 5.02it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.96it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 4.99it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.98it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:01, 5.01it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 4.97it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 4.99it/s][A
62%|██████▎ | 15/24 [00:03<00:01, 4.96it/s]
Total progress: 67%|██████▋ | 16/24 [00:03<00:01, 4.97it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.95it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 4.96it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.96it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 4.97it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.97it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 4.98it/s][A
79%|███████▉ | 19/24 [00:03<00:01, 4.96it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 4.96it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 4.97it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 4.97it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 4.98it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 4.99it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.97it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.97it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.96it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.97it/s][A
100%|██████████| 24/24 [00:04<00:00, 4.97it/s]
100%|██████████| 24/24 [00:04<00:00, 4.99it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 2474.44 MB ... Unload model JointTextEncoder Current free memory is 4233.30 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 4233.30 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3049.74 MB, All loaded to GPU.
Moving model(s) has taken 0.67 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.97it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.24it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4070.37 MB ... Unload model KModel Current free memory is 9070.76 MB ... Unload model IntegratedAutoencoderKL Done.
################################################################
[1m[32mInstall script for stable-diffusion + Web UI
[1m[34mTested on Debian 11 (Bullseye), Fedora 34+ and openSUSE Leap 15.4 or newer.[0m
################################################################
################################################################
Running on [1m[32mroot[0m user
################################################################
################################################################
Repo already cloned, using it as install directory
################################################################
################################################################
Create and activate python venv
################################################################
################################################################
Launching launch.py...
################################################################
glibc version is 2.39
Check TCMalloc: libtcmalloc_minimal.so.4
libtcmalloc_minimal.so.4 is linked with libc.so,execute LD_PRELOAD=/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4
=============================================================================================
INCOMPATIBLE PYTHON VERSION
This program is tested with 3.10.6 Python, but you have 3.12.3.
If you encounter an error with "RuntimeError: Couldn't install torch." message,
or any other error regarding unsuccessful package (library) installation,
please downgrade (or upgrade) to the latest version of 3.10 Python
and delete current Python and "venv" folder in WebUI's directory.
You can download 3.10 Python from here: https://www.python.org/downloads/release/python-3106/
Use --skip-python-version-check to suppress this warning.
=============================================================================================
Python 3.12.3 (main, Jan 22 2026, 20:57:42) [GCC 13.3.0]
Version: f2.0.1v1.10.1-previous-669-gdfdcbab6
Commit hash: dfdcbab685e57677014f05a3309b48cc87383167
Legacy Preprocessor init warning: Unable to install insightface automatically. Please try run `pip install insightface` manually.
Launching Web UI with arguments: -f --listen --api --enable-insecure-extension-access --xformers --no-half-vae --port 7887
Total VRAM 20017 MB, total RAM 64105 MB
pytorch version: 2.3.1+cu121
WARNING:xformers:A matching Triton is not available, some optimizations will not be enabled
Traceback (most recent call last):
File "/opt/sd-webui/venv/lib/python3.12/site-packages/xformers/__init__.py", line 57, in _is_triton_available
import triton # noqa
^^^^^^^^^^^^^
ModuleNotFoundError: No module named 'triton'
xformers version: 0.0.27
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA RTX 4000 SFF Ada Generation : native
Hint: your device supports --cuda-malloc for potential speed improvements.
VAE dtype preferences: [torch.bfloat16, torch.float32] -> torch.bfloat16
CUDA Using Stream: False
Using xformers cross attention
Using xformers attention for VAE
ControlNet preprocessor location: /opt/sd-webui/models/ControlNetPreprocessor
*** Error loading script: soft_inpainting.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 525, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/sd-webui/modules/script_loading.py", line 13, in load_module
module_spec.loader.exec_module(module)
File "<frozen importlib._bootstrap_external>", line 995, in exec_module
File "<frozen importlib._bootstrap>", line 488, in _call_with_frames_removed
File "/opt/sd-webui/extensions-builtin/soft-inpainting/scripts/soft_inpainting.py", line 10, in <module>
from joblib import Parallel, delayed, cpu_count
ModuleNotFoundError: No module named 'joblib'
---
2026-02-26 11:57:16,452 - ControlNet - [0;32mINFO[0m - ControlNet UI callback registered.
Model selected: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
Using online LoRAs in FP16: False
Running on local URL: http://0.0.0.0:7887
To create a public link, set `share=True` in `launch()`.
Loading Model: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Done.
Startup time: 8.9s (prepare environment: 1.5s, launcher: 0.2s, import torch: 3.6s, other imports: 0.1s, load scripts: 0.8s, create ui: 1.2s, gradio launch: 0.6s, add APIs: 0.9s).
StateDict Keys: {'unet': 1680, 'vae': 248, 'text_encoder': 197, 'text_encoder_2': 518, 'ignore': 0}
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
K-Model Created: {'storage_dtype': torch.float16, 'computation_dtype': torch.float16}
Model loaded in 0.8s (unload existing model: 0.1s, forge model load: 0.7s).
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3051.58 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 9306.96 MB, Model Require: 1559.68 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 6723.28 MB, All loaded to GPU.
Moving model(s) has taken 0.56 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 7503.26 MB ... Done.
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 7502.50 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 7502.50 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 1581.46 MB, All loaded to GPU.
Moving model(s) has taken 1.89 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
4%|▍ | 1/24 [00:00<00:06, 3.51it/s]
8%|▊ | 2/24 [00:00<00:05, 4.31it/s]
Total progress: 12%|█▎ | 3/24 [00:00<00:02, 10.41it/s][A
12%|█▎ | 3/24 [00:00<00:04, 4.62it/s]
17%|█▋ | 4/24 [00:00<00:04, 4.77it/s]
Total progress: 21%|██ | 5/24 [00:00<00:02, 6.84it/s][A
21%|██ | 5/24 [00:01<00:03, 4.86it/s]
Total progress: 25%|██▌ | 6/24 [00:00<00:02, 6.26it/s][A
25%|██▌ | 6/24 [00:01<00:03, 4.92it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:02, 5.87it/s][A
29%|██▉ | 7/24 [00:01<00:03, 4.95it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:02, 5.61it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.97it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.42it/s][A
38%|███▊ | 9/24 [00:01<00:03, 4.97it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.28it/s][A
42%|████▏ | 10/24 [00:02<00:02, 4.97it/s]
Total progress: 46%|████▌ | 11/24 [00:01<00:02, 5.19it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.97it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 5.12it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.97it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 5.08it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.99it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:01, 5.06it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 5.00it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 5.05it/s][A
62%|██████▎ | 15/24 [00:03<00:01, 5.00it/s]
Total progress: 67%|██████▋ | 16/24 [00:02<00:01, 5.04it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 5.00it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 5.02it/s][A
71%|███████ | 17/24 [00:03<00:01, 5.00it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 5.02it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 5.00it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:00, 5.01it/s][A
79%|███████▉ | 19/24 [00:03<00:00, 5.01it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 5.02it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 5.01it/s]
Total progress: 88%|████████▊ | 21/24 [00:03<00:00, 5.01it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 5.00it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 5.00it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.98it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.98it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.97it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.97it/s][A
100%|██████████| 24/24 [00:04<00:00, 4.97it/s]
100%|██████████| 24/24 [00:04<00:00, 4.92it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 2484.88 MB ... Unload model JointTextEncoder Current free memory is 4245.24 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 4245.24 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3061.68 MB, All loaded to GPU.
Moving model(s) has taken 0.75 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.97it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.27it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4076.19 MB ... Unload model KModel Current free memory is 9073.53 MB ... Unload model IntegratedAutoencoderKL Done.
################################################################
[1m[32mInstall script for stable-diffusion + Web UI
[1m[34mTested on Debian 11 (Bullseye), Fedora 34+ and openSUSE Leap 15.4 or newer.[0m
################################################################
################################################################
Running on [1m[32mroot[0m user
################################################################
################################################################
Repo already cloned, using it as install directory
################################################################
################################################################
Create and activate python venv
################################################################
################################################################
Launching launch.py...
################################################################
glibc version is 2.39
Check TCMalloc: libtcmalloc_minimal.so.4
libtcmalloc_minimal.so.4 is linked with libc.so,execute LD_PRELOAD=/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4
=============================================================================================
INCOMPATIBLE PYTHON VERSION
This program is tested with 3.10.6 Python, but you have 3.12.3.
If you encounter an error with "RuntimeError: Couldn't install torch." message,
or any other error regarding unsuccessful package (library) installation,
please downgrade (or upgrade) to the latest version of 3.10 Python
and delete current Python and "venv" folder in WebUI's directory.
You can download 3.10 Python from here: https://www.python.org/downloads/release/python-3106/
Use --skip-python-version-check to suppress this warning.
=============================================================================================
Python 3.12.3 (main, Jan 22 2026, 20:57:42) [GCC 13.3.0]
Version: f2.0.1v1.10.1-previous-669-gdfdcbab6
Commit hash: dfdcbab685e57677014f05a3309b48cc87383167
Legacy Preprocessor init warning: Unable to install insightface automatically. Please try run `pip install insightface` manually.
Launching Web UI with arguments: -f --listen --api --enable-insecure-extension-access --xformers --no-half-vae --port 7887
Total VRAM 20017 MB, total RAM 64105 MB
pytorch version: 2.3.1+cu121
WARNING:xformers:A matching Triton is not available, some optimizations will not be enabled
Traceback (most recent call last):
File "/opt/sd-webui/venv/lib/python3.12/site-packages/xformers/__init__.py", line 57, in _is_triton_available
import triton # noqa
^^^^^^^^^^^^^
ModuleNotFoundError: No module named 'triton'
xformers version: 0.0.27
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA RTX 4000 SFF Ada Generation : native
Hint: your device supports --cuda-malloc for potential speed improvements.
VAE dtype preferences: [torch.bfloat16, torch.float32] -> torch.bfloat16
CUDA Using Stream: False
Using xformers cross attention
Using xformers attention for VAE
ControlNet preprocessor location: /opt/sd-webui/models/ControlNetPreprocessor
*** Error loading script: soft_inpainting.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 525, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/sd-webui/modules/script_loading.py", line 13, in load_module
module_spec.loader.exec_module(module)
File "<frozen importlib._bootstrap_external>", line 995, in exec_module
File "<frozen importlib._bootstrap>", line 488, in _call_with_frames_removed
File "/opt/sd-webui/extensions-builtin/soft-inpainting/scripts/soft_inpainting.py", line 10, in <module>
from joblib import Parallel, delayed, cpu_count
ModuleNotFoundError: No module named 'joblib'
---
2026-02-26 12:41:04,187 - ControlNet - [0;32mINFO[0m - ControlNet UI callback registered.
Model selected: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
Using online LoRAs in FP16: False
Running on local URL: http://0.0.0.0:7887
To create a public link, set `share=True` in `launch()`.
Loading Model: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Done.
Startup time: 9.5s (prepare environment: 1.7s, launcher: 0.3s, import torch: 3.9s, other imports: 0.2s, load scripts: 0.9s, create ui: 1.1s, gradio launch: 0.5s, add APIs: 0.9s).
StateDict Keys: {'unet': 1680, 'vae': 248, 'text_encoder': 197, 'text_encoder_2': 518, 'ignore': 0}
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
K-Model Created: {'storage_dtype': torch.float16, 'computation_dtype': torch.float16}
Model loaded in 1.3s (unload existing model: 0.1s, forge model load: 1.2s).
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3051.58 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 9306.96 MB, Model Require: 1559.68 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 6723.28 MB, All loaded to GPU.
Moving model(s) has taken 1.18 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 7503.26 MB ... Done.
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 7502.50 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 7502.50 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 1581.46 MB, All loaded to GPU.
Moving model(s) has taken 4.19 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
4%|▍ | 1/24 [00:00<00:10, 2.21it/s]
8%|▊ | 2/24 [00:00<00:06, 3.33it/s]
Total progress: 12%|█▎ | 3/24 [00:00<00:02, 10.39it/s][A
12%|█▎ | 3/24 [00:00<00:05, 3.94it/s]
17%|█▋ | 4/24 [00:01<00:04, 4.30it/s]
Total progress: 21%|██ | 5/24 [00:00<00:02, 6.81it/s][A
21%|██ | 5/24 [00:01<00:04, 4.54it/s]
Total progress: 25%|██▌ | 6/24 [00:00<00:02, 6.23it/s][A
25%|██▌ | 6/24 [00:01<00:03, 4.68it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:02, 5.85it/s][A
29%|██▉ | 7/24 [00:01<00:03, 4.79it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:02, 5.59it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.86it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.42it/s][A
38%|███▊ | 9/24 [00:02<00:03, 4.90it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.29it/s][A
42%|████▏ | 10/24 [00:02<00:02, 4.94it/s]
Total progress: 46%|████▌ | 11/24 [00:01<00:02, 5.20it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.95it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 5.14it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.96it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 5.09it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.97it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:01, 5.06it/s][A
58%|█████▊ | 14/24 [00:03<00:02, 4.98it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 5.05it/s][A
62%|██████▎ | 15/24 [00:03<00:01, 4.99it/s]
Total progress: 67%|██████▋ | 16/24 [00:02<00:01, 5.05it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 5.01it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 5.04it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.99it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 5.01it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.99it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:00, 5.00it/s][A
79%|███████▉ | 19/24 [00:04<00:01, 5.00it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 5.01it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 4.99it/s]
Total progress: 88%|████████▊ | 21/24 [00:03<00:00, 5.00it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 4.99it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 5.00it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 5.01it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 5.01it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 5.01it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 5.00it/s][A
100%|██████████| 24/24 [00:05<00:00, 4.98it/s]
100%|██████████| 24/24 [00:05<00:00, 4.76it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 2484.88 MB ... Unload model JointTextEncoder Current free memory is 4245.24 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 4245.24 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3061.68 MB, All loaded to GPU.
Moving model(s) has taken 0.78 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 5.00it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.21it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4076.19 MB ... Unload model KModel Current free memory is 9073.53 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 9234.72 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 6457.74 MB, All loaded to GPU.
Moving model(s) has taken 0.61 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 7475.25 MB ... Done.
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 7474.50 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 7474.50 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 1553.45 MB, All loaded to GPU.
Moving model(s) has taken 1.68 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
Total progress: 8%|▊ | 2/24 [00:00<00:02, 9.97it/s][A
8%|▊ | 2/24 [00:00<00:04, 5.12it/s]
Total progress: 12%|█▎ | 3/24 [00:00<00:02, 7.07it/s][A
12%|█▎ | 3/24 [00:00<00:04, 5.07it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 6.11it/s][A
17%|█▋ | 4/24 [00:00<00:03, 5.05it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.68it/s][A
21%|██ | 5/24 [00:00<00:03, 5.01it/s]
Total progress: 25%|██▌ | 6/24 [00:01<00:03, 5.42it/s][A
25%|██▌ | 6/24 [00:01<00:03, 5.01it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.27it/s][A
29%|██▉ | 7/24 [00:01<00:03, 5.00it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.19it/s][A
33%|███▎ | 8/24 [00:01<00:03, 5.00it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.13it/s][A
38%|███▊ | 9/24 [00:01<00:02, 5.01it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.09it/s][A
42%|████▏ | 10/24 [00:01<00:02, 5.01it/s]
Total progress: 46%|████▌ | 11/24 [00:02<00:02, 5.07it/s][A
46%|████▌ | 11/24 [00:02<00:02, 5.01it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 5.05it/s][A
50%|█████ | 12/24 [00:02<00:02, 5.00it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 5.02it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 5.00it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:01, 5.02it/s][A
58%|█████▊ | 14/24 [00:02<00:01, 5.00it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 5.01it/s][A
62%|██████▎ | 15/24 [00:02<00:01, 5.00it/s]
Total progress: 67%|██████▋ | 16/24 [00:03<00:01, 5.01it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 5.00it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 5.00it/s][A
71%|███████ | 17/24 [00:03<00:01, 5.01it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 5.01it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.99it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 4.99it/s][A
79%|███████▉ | 19/24 [00:03<00:01, 4.99it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 4.99it/s][A
83%|████████▎ | 20/24 [00:03<00:00, 5.00it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 5.00it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 4.99it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 5.00it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.98it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.99it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.99it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 5.00it/s][A
100%|██████████| 24/24 [00:04<00:00, 4.99it/s]
100%|██████████| 24/24 [00:04<00:00, 5.00it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 2473.83 MB ... Unload model JointTextEncoder Current free memory is 4232.69 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 4232.69 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3049.13 MB, All loaded to GPU.
Moving model(s) has taken 0.68 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 5.00it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.25it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4069.76 MB ... Unload model KModel Current free memory is 9070.14 MB ... Unload model IntegratedAutoencoderKL Done.
################################################################
[1m[32mInstall script for stable-diffusion + Web UI
[1m[34mTested on Debian 11 (Bullseye), Fedora 34+ and openSUSE Leap 15.4 or newer.[0m
################################################################
################################################################
Running on [1m[32mroot[0m user
################################################################
################################################################
Repo already cloned, using it as install directory
################################################################
################################################################
Create and activate python venv
################################################################
################################################################
Launching launch.py...
################################################################
glibc version is 2.39
Check TCMalloc: libtcmalloc_minimal.so.4
libtcmalloc_minimal.so.4 is linked with libc.so,execute LD_PRELOAD=/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4
=============================================================================================
INCOMPATIBLE PYTHON VERSION
This program is tested with 3.10.6 Python, but you have 3.12.3.
If you encounter an error with "RuntimeError: Couldn't install torch." message,
or any other error regarding unsuccessful package (library) installation,
please downgrade (or upgrade) to the latest version of 3.10 Python
and delete current Python and "venv" folder in WebUI's directory.
You can download 3.10 Python from here: https://www.python.org/downloads/release/python-3106/
Use --skip-python-version-check to suppress this warning.
=============================================================================================
Python 3.12.3 (main, Jan 22 2026, 20:57:42) [GCC 13.3.0]
Version: f2.0.1v1.10.1-previous-669-gdfdcbab6
Commit hash: dfdcbab685e57677014f05a3309b48cc87383167
Legacy Preprocessor init warning: Unable to install insightface automatically. Please try run `pip install insightface` manually.
Launching Web UI with arguments: -f --listen --api --enable-insecure-extension-access --xformers --no-half-vae --port 7887
Total VRAM 20017 MB, total RAM 64105 MB
pytorch version: 2.3.1+cu121
WARNING:xformers:A matching Triton is not available, some optimizations will not be enabled
Traceback (most recent call last):
File "/opt/sd-webui/venv/lib/python3.12/site-packages/xformers/__init__.py", line 57, in _is_triton_available
import triton # noqa
^^^^^^^^^^^^^
ModuleNotFoundError: No module named 'triton'
xformers version: 0.0.27
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA RTX 4000 SFF Ada Generation : native
Hint: your device supports --cuda-malloc for potential speed improvements.
VAE dtype preferences: [torch.bfloat16, torch.float32] -> torch.bfloat16
CUDA Using Stream: False
Using xformers cross attention
Using xformers attention for VAE
ControlNet preprocessor location: /opt/sd-webui/models/ControlNetPreprocessor
*** Error loading script: soft_inpainting.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 525, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/sd-webui/modules/script_loading.py", line 13, in load_module
module_spec.loader.exec_module(module)
File "<frozen importlib._bootstrap_external>", line 995, in exec_module
File "<frozen importlib._bootstrap>", line 488, in _call_with_frames_removed
File "/opt/sd-webui/extensions-builtin/soft-inpainting/scripts/soft_inpainting.py", line 10, in <module>
from joblib import Parallel, delayed, cpu_count
ModuleNotFoundError: No module named 'joblib'
---
2026-02-26 12:55:23,195 - ControlNet - [0;32mINFO[0m - ControlNet UI callback registered.
Model selected: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
Using online LoRAs in FP16: False
Running on local URL: http://0.0.0.0:7887
To create a public link, set `share=True` in `launch()`.
Loading Model: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Done.
StateDict Keys: {'unet': 1680, 'vae': 248, 'text_encoder': 197, 'text_encoder_2': 518, 'ignore': 0}
Startup time: 8.1s (prepare environment: 1.2s, launcher: 0.2s, import torch: 3.1s, other imports: 0.1s, load scripts: 0.8s, create ui: 1.1s, gradio launch: 0.5s, add APIs: 1.0s).
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
K-Model Created: {'storage_dtype': torch.float16, 'computation_dtype': torch.float16}
Model loaded in 0.8s (unload existing model: 0.2s, forge model load: 0.6s).
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3051.58 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 9306.96 MB, Model Require: 1559.68 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 6723.28 MB, All loaded to GPU.
Moving model(s) has taken 0.58 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 7503.26 MB ... Done.
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 7502.50 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 7502.50 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 1581.46 MB, All loaded to GPU.
Moving model(s) has taken 1.88 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
4%|▍ | 1/24 [00:00<00:06, 3.56it/s]
8%|▊ | 2/24 [00:00<00:04, 4.42it/s]
Total progress: 12%|█▎ | 3/24 [00:00<00:01, 10.68it/s][A
12%|█▎ | 3/24 [00:00<00:04, 4.67it/s]
17%|█▋ | 4/24 [00:00<00:04, 4.79it/s]
Total progress: 21%|██ | 5/24 [00:00<00:02, 6.85it/s][A
21%|██ | 5/24 [00:01<00:03, 4.85it/s]
Total progress: 25%|██▌ | 6/24 [00:00<00:02, 6.24it/s][A
25%|██▌ | 6/24 [00:01<00:03, 4.90it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:02, 5.85it/s][A
29%|██▉ | 7/24 [00:01<00:03, 4.94it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:02, 5.59it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.95it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.41it/s][A
38%|███▊ | 9/24 [00:01<00:03, 4.97it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.29it/s][A
42%|████▏ | 10/24 [00:02<00:02, 4.98it/s]
Total progress: 46%|████▌ | 11/24 [00:01<00:02, 5.20it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.99it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 5.14it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.99it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 5.10it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.99it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:01, 5.07it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 4.99it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 5.04it/s][A
62%|██████▎ | 15/24 [00:03<00:01, 5.00it/s]
Total progress: 67%|██████▋ | 16/24 [00:02<00:01, 5.03it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.99it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 5.01it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.99it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 5.00it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.97it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 4.99it/s][A
79%|███████▉ | 19/24 [00:03<00:01, 4.98it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 4.99it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 4.99it/s]
Total progress: 88%|████████▊ | 21/24 [00:03<00:00, 4.99it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 5.00it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 4.99it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.99it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.99it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.99it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.99it/s][A
100%|██████████| 24/24 [00:04<00:00, 4.99it/s]
100%|██████████| 24/24 [00:04<00:00, 4.92it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 2484.88 MB ... Unload model JointTextEncoder Current free memory is 4245.24 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 4245.24 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3061.68 MB, All loaded to GPU.
Moving model(s) has taken 0.89 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.99it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.16it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4076.19 MB ... Unload model KModel Current free memory is 9073.53 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 9234.72 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 6457.74 MB, All loaded to GPU.
Moving model(s) has taken 0.63 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 7476.76 MB ... Done.
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 7476.00 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 7476.00 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 1554.96 MB, All loaded to GPU.
Moving model(s) has taken 1.73 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
Total progress: 8%|▊ | 2/24 [00:00<00:02, 9.96it/s][A
8%|▊ | 2/24 [00:00<00:04, 5.11it/s]
Total progress: 12%|█▎ | 3/24 [00:00<00:02, 7.03it/s][A
12%|█▎ | 3/24 [00:00<00:04, 5.07it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 6.11it/s][A
17%|█▋ | 4/24 [00:00<00:03, 5.03it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.65it/s][A
21%|██ | 5/24 [00:00<00:03, 5.01it/s]
Total progress: 25%|██▌ | 6/24 [00:01<00:03, 5.40it/s][A
25%|██▌ | 6/24 [00:01<00:03, 4.99it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.25it/s][A
29%|██▉ | 7/24 [00:01<00:03, 4.98it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.16it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.98it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.10it/s][A
38%|███▊ | 9/24 [00:01<00:03, 4.98it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.07it/s][A
42%|████▏ | 10/24 [00:01<00:02, 4.99it/s]
Total progress: 46%|████▌ | 11/24 [00:02<00:02, 5.06it/s][A
46%|████▌ | 11/24 [00:02<00:02, 5.00it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 5.05it/s][A
50%|█████ | 12/24 [00:02<00:02, 5.01it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 5.04it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.99it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:01, 5.01it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 5.00it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 5.01it/s][A
62%|██████▎ | 15/24 [00:02<00:01, 5.00it/s]
Total progress: 67%|██████▋ | 16/24 [00:03<00:01, 5.01it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 5.00it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 5.00it/s][A
71%|███████ | 17/24 [00:03<00:01, 5.01it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 5.01it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 5.00it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:00, 5.01it/s][A
79%|███████▉ | 19/24 [00:03<00:00, 5.01it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 5.01it/s][A
83%|████████▎ | 20/24 [00:03<00:00, 5.00it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 5.00it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 5.00it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 5.00it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 5.01it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 5.00it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.99it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.99it/s][A
100%|██████████| 24/24 [00:04<00:00, 4.99it/s]
100%|██████████| 24/24 [00:04<00:00, 5.00it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 2475.34 MB ... Unload model JointTextEncoder Current free memory is 4234.19 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 4234.19 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3050.64 MB, All loaded to GPU.
Moving model(s) has taken 0.68 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.99it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.25it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4071.26 MB ... Unload model KModel Current free memory is 9071.65 MB ... Unload model IntegratedAutoencoderKL Done.
################################################################
[1m[32mInstall script for stable-diffusion + Web UI
[1m[34mTested on Debian 11 (Bullseye), Fedora 34+ and openSUSE Leap 15.4 or newer.[0m
################################################################
################################################################
Running on [1m[32mroot[0m user
################################################################
################################################################
Repo already cloned, using it as install directory
################################################################
################################################################
Create and activate python venv
################################################################
################################################################
Launching launch.py...
################################################################
glibc version is 2.39
Check TCMalloc: libtcmalloc_minimal.so.4
libtcmalloc_minimal.so.4 is linked with libc.so,execute LD_PRELOAD=/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4
=============================================================================================
INCOMPATIBLE PYTHON VERSION
This program is tested with 3.10.6 Python, but you have 3.12.3.
If you encounter an error with "RuntimeError: Couldn't install torch." message,
or any other error regarding unsuccessful package (library) installation,
please downgrade (or upgrade) to the latest version of 3.10 Python
and delete current Python and "venv" folder in WebUI's directory.
You can download 3.10 Python from here: https://www.python.org/downloads/release/python-3106/
Use --skip-python-version-check to suppress this warning.
=============================================================================================
Python 3.12.3 (main, Jan 22 2026, 20:57:42) [GCC 13.3.0]
Version: f2.0.1v1.10.1-previous-669-gdfdcbab6
Commit hash: dfdcbab685e57677014f05a3309b48cc87383167
Legacy Preprocessor init warning: Unable to install insightface automatically. Please try run `pip install insightface` manually.
Launching Web UI with arguments: -f --listen --api --enable-insecure-extension-access --xformers --no-half-vae --port 7887
Total VRAM 20017 MB, total RAM 64105 MB
pytorch version: 2.3.1+cu121
WARNING:xformers:A matching Triton is not available, some optimizations will not be enabled
Traceback (most recent call last):
File "/opt/sd-webui/venv/lib/python3.12/site-packages/xformers/__init__.py", line 57, in _is_triton_available
import triton # noqa
^^^^^^^^^^^^^
ModuleNotFoundError: No module named 'triton'
xformers version: 0.0.27
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA RTX 4000 SFF Ada Generation : native
Hint: your device supports --cuda-malloc for potential speed improvements.
VAE dtype preferences: [torch.bfloat16, torch.float32] -> torch.bfloat16
CUDA Using Stream: False
Using xformers cross attention
Using xformers attention for VAE
ControlNet preprocessor location: /opt/sd-webui/models/ControlNetPreprocessor
*** Error loading script: soft_inpainting.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 525, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/sd-webui/modules/script_loading.py", line 13, in load_module
module_spec.loader.exec_module(module)
File "<frozen importlib._bootstrap_external>", line 995, in exec_module
File "<frozen importlib._bootstrap>", line 488, in _call_with_frames_removed
File "/opt/sd-webui/extensions-builtin/soft-inpainting/scripts/soft_inpainting.py", line 10, in <module>
from joblib import Parallel, delayed, cpu_count
ModuleNotFoundError: No module named 'joblib'
---
2026-02-26 16:53:10,846 - ControlNet - [0;32mINFO[0m - ControlNet UI callback registered.
Model selected: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
Using online LoRAs in FP16: False
Running on local URL: http://0.0.0.0:7887
To create a public link, set `share=True` in `launch()`.
Loading Model: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Done.
Startup time: 9.6s (prepare environment: 1.9s, launcher: 0.3s, import torch: 3.9s, other imports: 0.2s, load scripts: 0.9s, create ui: 1.1s, gradio launch: 0.5s, add APIs: 0.9s).
StateDict Keys: {'unet': 1680, 'vae': 248, 'text_encoder': 197, 'text_encoder_2': 518, 'ignore': 0}
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
K-Model Created: {'storage_dtype': torch.float16, 'computation_dtype': torch.float16}
Model loaded in 1.4s (unload existing model: 0.1s, forge model load: 1.3s).
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3051.58 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 11910.96 MB, Model Require: 1559.68 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 9327.28 MB, All loaded to GPU.
Moving model(s) has taken 1.03 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 10107.26 MB ... Done.
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 10106.50 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 10106.50 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 4185.46 MB, All loaded to GPU.
Moving model(s) has taken 3.37 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
4%|▍ | 1/24 [00:00<00:10, 2.17it/s]
8%|▊ | 2/24 [00:00<00:06, 3.28it/s]
Total progress: 12%|█▎ | 3/24 [00:00<00:02, 10.36it/s][A
12%|█▎ | 3/24 [00:00<00:05, 3.91it/s]
17%|█▋ | 4/24 [00:01<00:04, 4.29it/s]
Total progress: 21%|██ | 5/24 [00:00<00:02, 6.82it/s][A
21%|██ | 5/24 [00:01<00:04, 4.52it/s]
Total progress: 25%|██▌ | 6/24 [00:00<00:02, 6.23it/s][A
25%|██▌ | 6/24 [00:01<00:03, 4.67it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:02, 5.85it/s][A
29%|██▉ | 7/24 [00:01<00:03, 4.78it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:02, 5.58it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.84it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.41it/s][A
38%|███▊ | 9/24 [00:02<00:03, 4.88it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.28it/s][A
42%|████▏ | 10/24 [00:02<00:02, 4.93it/s]
Total progress: 46%|████▌ | 11/24 [00:01<00:02, 5.20it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.95it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 5.14it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.97it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 5.10it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.97it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:01, 5.08it/s][A
58%|█████▊ | 14/24 [00:03<00:01, 5.02it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 5.08it/s][A
62%|██████▎ | 15/24 [00:03<00:01, 5.00it/s]
Total progress: 67%|██████▋ | 16/24 [00:02<00:01, 5.04it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 5.00it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 5.03it/s][A
71%|███████ | 17/24 [00:03<00:01, 5.01it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 5.03it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 5.00it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:00, 5.01it/s][A
79%|███████▉ | 19/24 [00:04<00:00, 5.01it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 5.02it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 5.01it/s]
Total progress: 88%|████████▊ | 21/24 [00:03<00:00, 5.01it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 5.00it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 5.01it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.99it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 5.00it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 5.01it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 5.01it/s][A
100%|██████████| 24/24 [00:05<00:00, 4.99it/s]
100%|██████████| 24/24 [00:05<00:00, 4.75it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 5088.88 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 5088.88 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3905.33 MB, All loaded to GPU.
Moving model(s) has taken 0.06 seconds
Total progress: 100%|██████████| 24/24 [00:04<00:00, 5.01it/s][A
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.84it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4919.46 MB ... Unload model JointTextEncoder Current free memory is 6679.81 MB ... Unload model KModel Current free memory is 11677.15 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 11838.72 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 9061.74 MB, All loaded to GPU.
Moving model(s) has taken 0.60 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 10079.25 MB ... Done.
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 10078.50 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 10078.50 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 4157.45 MB, All loaded to GPU.
Moving model(s) has taken 1.67 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
Total progress: 8%|▊ | 2/24 [00:00<00:02, 10.00it/s][A
8%|▊ | 2/24 [00:00<00:04, 5.17it/s]
12%|█▎ | 3/24 [00:00<00:04, 5.11it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 6.34it/s][A
17%|█▋ | 4/24 [00:00<00:03, 5.08it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.87it/s][A
21%|██ | 5/24 [00:00<00:03, 5.04it/s]
Total progress: 25%|██▌ | 6/24 [00:00<00:03, 5.57it/s][A
25%|██▌ | 6/24 [00:01<00:03, 5.02it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.38it/s][A
29%|██▉ | 7/24 [00:01<00:03, 5.00it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.24it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.99it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.15it/s][A
38%|███▊ | 9/24 [00:01<00:03, 4.98it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.10it/s][A
42%|████▏ | 10/24 [00:01<00:02, 4.99it/s]
Total progress: 46%|████▌ | 11/24 [00:02<00:02, 5.07it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.98it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 5.03it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.97it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 5.01it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.97it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:02, 4.99it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 4.97it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 4.99it/s][A
62%|██████▎ | 15/24 [00:02<00:01, 4.97it/s]
Total progress: 67%|██████▋ | 16/24 [00:03<00:01, 4.99it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.98it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 4.99it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.97it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 4.98it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.97it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 4.97it/s][A
79%|███████▉ | 19/24 [00:03<00:01, 4.97it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 4.98it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 4.99it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 4.99it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 4.98it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 4.99it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 5.00it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 5.00it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.99it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 5.00it/s][A
100%|██████████| 24/24 [00:04<00:00, 5.00it/s]
100%|██████████| 24/24 [00:04<00:00, 5.00it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 5077.83 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 5077.83 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3894.27 MB, All loaded to GPU.
Moving model(s) has taken 0.06 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 5.00it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.77it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4916.40 MB ... Unload model JointTextEncoder Current free memory is 6675.26 MB ... Unload model KModel Current free memory is 11675.64 MB ... Unload model IntegratedAutoencoderKL Done.
################################################################
[1m[32mInstall script for stable-diffusion + Web UI
[1m[34mTested on Debian 11 (Bullseye), Fedora 34+ and openSUSE Leap 15.4 or newer.[0m
################################################################
################################################################
Running on [1m[32mroot[0m user
################################################################
################################################################
Repo already cloned, using it as install directory
################################################################
################################################################
Create and activate python venv
################################################################
################################################################
Launching launch.py...
################################################################
glibc version is 2.39
Check TCMalloc: libtcmalloc_minimal.so.4
libtcmalloc_minimal.so.4 is linked with libc.so,execute LD_PRELOAD=/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4
=============================================================================================
INCOMPATIBLE PYTHON VERSION
This program is tested with 3.10.6 Python, but you have 3.12.3.
If you encounter an error with "RuntimeError: Couldn't install torch." message,
or any other error regarding unsuccessful package (library) installation,
please downgrade (or upgrade) to the latest version of 3.10 Python
and delete current Python and "venv" folder in WebUI's directory.
You can download 3.10 Python from here: https://www.python.org/downloads/release/python-3106/
Use --skip-python-version-check to suppress this warning.
=============================================================================================
Python 3.12.3 (main, Jan 22 2026, 20:57:42) [GCC 13.3.0]
Version: f2.0.1v1.10.1-previous-669-gdfdcbab6
Commit hash: dfdcbab685e57677014f05a3309b48cc87383167
Legacy Preprocessor init warning: Unable to install insightface automatically. Please try run `pip install insightface` manually.
Launching Web UI with arguments: -f --listen --api --enable-insecure-extension-access --xformers --no-half-vae --port 7887
Total VRAM 20017 MB, total RAM 64105 MB
pytorch version: 2.3.1+cu121
WARNING:xformers:A matching Triton is not available, some optimizations will not be enabled
Traceback (most recent call last):
File "/opt/sd-webui/venv/lib/python3.12/site-packages/xformers/__init__.py", line 57, in _is_triton_available
import triton # noqa
^^^^^^^^^^^^^
ModuleNotFoundError: No module named 'triton'
xformers version: 0.0.27
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA RTX 4000 SFF Ada Generation : native
Hint: your device supports --cuda-malloc for potential speed improvements.
VAE dtype preferences: [torch.bfloat16, torch.float32] -> torch.bfloat16
CUDA Using Stream: False
Using xformers cross attention
Using xformers attention for VAE
ControlNet preprocessor location: /opt/sd-webui/models/ControlNetPreprocessor
*** Error loading script: soft_inpainting.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 525, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/sd-webui/modules/script_loading.py", line 13, in load_module
module_spec.loader.exec_module(module)
File "<frozen importlib._bootstrap_external>", line 995, in exec_module
File "<frozen importlib._bootstrap>", line 488, in _call_with_frames_removed
File "/opt/sd-webui/extensions-builtin/soft-inpainting/scripts/soft_inpainting.py", line 10, in <module>
from joblib import Parallel, delayed, cpu_count
ModuleNotFoundError: No module named 'joblib'
---
2026-02-26 17:41:55,103 - ControlNet - [0;32mINFO[0m - ControlNet UI callback registered.
Model selected: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
Using online LoRAs in FP16: False
Running on local URL: http://0.0.0.0:7887
To create a public link, set `share=True` in `launch()`.
Loading Model: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Done.
Startup time: 9.6s (prepare environment: 1.8s, launcher: 0.3s, import torch: 3.8s, other imports: 0.2s, load scripts: 0.8s, create ui: 1.1s, gradio launch: 0.5s, add APIs: 1.0s).
StateDict Keys: {'unet': 1680, 'vae': 248, 'text_encoder': 197, 'text_encoder_2': 518, 'ignore': 0}
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
K-Model Created: {'storage_dtype': torch.float16, 'computation_dtype': torch.float16}
Model loaded in 1.7s (unload existing model: 0.1s, forge model load: 1.5s).
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
*** Error running process: /opt/sd-webui/extensions-builtin/sd_forge_neveroom/scripts/forge_never_oom.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 844, in process
script.process(p, *script_args)
File "/opt/sd-webui/extensions-builtin/sd_forge_neveroom/scripts/forge_never_oom.py", line 27, in process
unet_enabled, vae_enabled = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 2, got 0)
---
[Unload] Trying to free 3051.58 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 12152.08 MB, Model Require: 1559.68 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 9568.41 MB, All loaded to GPU.
Moving model(s) has taken 1.02 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 10348.38 MB ... Done.
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_dynamic_thresholding/scripts/forge_dynamic_thresholding.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_dynamic_thresholding/scripts/forge_dynamic_thresholding.py", line 49, in process_before_every_sampling
enabled, mimic_scale, threshold_percentile, mimic_mode, mimic_scale_min, cfg_mode, cfg_scale_min, \
ValueError: not enough values to unpack (expected 12, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_freeu/scripts/forge_freeu.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_freeu/scripts/forge_freeu.py", line 143, in process_before_every_sampling
freeu_enabled, freeu_b1, freeu_b2, freeu_s1, freeu_s2, freeu_start, freeu_end = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 7, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_kohya_hrfix/scripts/kohya_hrfix.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_kohya_hrfix/scripts/kohya_hrfix.py", line 79, in process_before_every_sampling
enabled, block_number, downscale_factor, start_percent, end_percent, downscale_after_skip, downscale_method, upscale_method = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 8, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_latent_modifier/scripts/forge_latent_modifier.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_latent_modifier/scripts/forge_latent_modifier.py", line 96, in process_before_every_sampling
enabled, sharpness_multiplier, sharpness_method, tonemap_multiplier, tonemap_method, tonemap_percentile, contrast_multiplier, combat_method, combat_cfg_drift, rescale_cfg_phi, extra_noise_type, extra_noise_method, extra_noise_multiplier, extra_noise_lowpass, divisive_norm_size, divisive_norm_multiplier, spectral_mod_mode, spectral_mod_percentile, spectral_mod_multiplier, affect_uncond, dyn_cfg_augmentation = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 21, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_multidiffusion/scripts/forge_multidiffusion.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_multidiffusion/scripts/forge_multidiffusion.py", line 36, in process_before_every_sampling
enabled, method, tile_width, tile_height, tile_overlap, tile_batch_size = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 6, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_perturbed_attention/scripts/forge_perturbed_attention.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_perturbed_attention/scripts/forge_perturbed_attention.py", line 50, in process_before_every_sampling
enabled, scale, attenuation, start_step, end_step = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 5, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_sag/scripts/forge_sag.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_sag/scripts/forge_sag.py", line 197, in process_before_every_sampling
enabled, scale, blur_sigma, threshold = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 4, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_stylealign/scripts/forge_stylealign.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_stylealign/scripts/forge_stylealign.py", line 33, in process_before_every_sampling
shared_attention, strength = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 2, got 0)
---
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 10347.63 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 10347.63 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 4426.58 MB, All loaded to GPU.
Moving model(s) has taken 3.25 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
4%|▍ | 1/24 [00:00<00:10, 2.17it/s]
8%|▊ | 2/24 [00:00<00:06, 3.28it/s]
Total progress: 12%|█▎ | 3/24 [00:00<00:02, 10.42it/s][A
12%|█▎ | 3/24 [00:00<00:05, 3.93it/s]
17%|█▋ | 4/24 [00:01<00:04, 4.30it/s]
Total progress: 21%|██ | 5/24 [00:00<00:02, 6.85it/s][A
21%|██ | 5/24 [00:01<00:04, 4.53it/s]
Total progress: 25%|██▌ | 6/24 [00:00<00:02, 6.24it/s][A
25%|██▌ | 6/24 [00:01<00:03, 4.68it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:02, 5.86it/s][A
29%|██▉ | 7/24 [00:01<00:03, 4.78it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:02, 5.58it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.85it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.41it/s][A
38%|███▊ | 9/24 [00:02<00:03, 4.89it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.27it/s][A
42%|████▏ | 10/24 [00:02<00:02, 4.92it/s]
Total progress: 46%|████▌ | 11/24 [00:01<00:02, 5.19it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.95it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 5.14it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.97it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 5.10it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.97it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:01, 5.06it/s][A
58%|█████▊ | 14/24 [00:03<00:02, 4.97it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 5.03it/s][A
62%|██████▎ | 15/24 [00:03<00:01, 4.97it/s]
Total progress: 67%|██████▋ | 16/24 [00:02<00:01, 5.02it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.98it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 5.02it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.99it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 5.01it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 5.00it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:00, 5.01it/s][A
79%|███████▉ | 19/24 [00:04<00:01, 5.00it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 5.01it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 5.00it/s]
Total progress: 88%|████████▊ | 21/24 [00:03<00:00, 5.01it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 5.00it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 5.01it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 5.00it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 5.00it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 5.00it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 5.00it/s][A
100%|██████████| 24/24 [00:05<00:00, 5.00it/s]
100%|██████████| 24/24 [00:05<00:00, 4.75it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 5330.01 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 5330.01 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 4146.45 MB, All loaded to GPU.
Moving model(s) has taken 0.06 seconds
Total progress: 100%|██████████| 24/24 [00:04<00:00, 5.00it/s][A
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.84it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 5160.58 MB ... Unload model JointTextEncoder Current free memory is 6920.94 MB ... Unload model KModel Current free memory is 11918.28 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 12079.84 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 9302.87 MB, All loaded to GPU.
Moving model(s) has taken 0.60 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 10320.38 MB ... Done.
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 10319.62 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 10319.62 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 4398.57 MB, All loaded to GPU.
Moving model(s) has taken 1.68 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
Total progress: 8%|▊ | 2/24 [00:00<00:02, 10.05it/s][A
8%|▊ | 2/24 [00:00<00:04, 5.14it/s]
12%|█▎ | 3/24 [00:00<00:04, 5.09it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 6.31it/s][A
17%|█▋ | 4/24 [00:00<00:03, 5.04it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.84it/s][A
21%|██ | 5/24 [00:00<00:03, 5.01it/s]
Total progress: 25%|██▌ | 6/24 [00:01<00:03, 5.55it/s][A
25%|██▌ | 6/24 [00:01<00:03, 4.99it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.34it/s][A
29%|██▉ | 7/24 [00:01<00:03, 4.97it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.22it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.96it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.13it/s][A
38%|███▊ | 9/24 [00:01<00:03, 4.96it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.08it/s][A
42%|████▏ | 10/24 [00:02<00:02, 4.97it/s]
Total progress: 46%|████▌ | 11/24 [00:02<00:02, 5.05it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.96it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 5.02it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.96it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 5.00it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.97it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:02, 5.00it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 4.97it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 4.99it/s][A
62%|██████▎ | 15/24 [00:03<00:01, 4.97it/s]
Total progress: 67%|██████▋ | 16/24 [00:03<00:01, 4.99it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.97it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 4.98it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.98it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 4.99it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.98it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 4.98it/s][A
79%|███████▉ | 19/24 [00:03<00:01, 4.97it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 4.97it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 4.97it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 4.97it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 4.97it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 4.97it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.96it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.96it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.96it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.96it/s][A
100%|██████████| 24/24 [00:04<00:00, 4.96it/s]
100%|██████████| 24/24 [00:04<00:00, 4.98it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 5318.96 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 5318.96 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 4135.40 MB, All loaded to GPU.
Moving model(s) has taken 0.06 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.96it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.76it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 5157.53 MB ... Unload model JointTextEncoder Current free memory is 6916.38 MB ... Unload model KModel Current free memory is 11916.77 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 12078.34 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 9301.36 MB, All loaded to GPU.
Moving model(s) has taken 0.59 seconds
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 10318.73 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 10318.73 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 4397.68 MB, All loaded to GPU.
Moving model(s) has taken 1.67 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
Total progress: 8%|▊ | 2/24 [00:00<00:02, 10.09it/s][A
8%|▊ | 2/24 [00:00<00:04, 5.14it/s]
12%|█▎ | 3/24 [00:00<00:04, 5.07it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 6.29it/s][A
17%|█▋ | 4/24 [00:00<00:03, 5.03it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.84it/s][A
21%|██ | 5/24 [00:00<00:03, 5.01it/s]
Total progress: 25%|██▌ | 6/24 [00:01<00:03, 5.55it/s][A
25%|██▌ | 6/24 [00:01<00:03, 5.00it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.37it/s][A
29%|██▉ | 7/24 [00:01<00:03, 4.99it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.24it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.98it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.15it/s][A
38%|███▊ | 9/24 [00:01<00:03, 4.97it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.10it/s][A
42%|████▏ | 10/24 [00:01<00:02, 4.97it/s]
Total progress: 46%|████▌ | 11/24 [00:02<00:02, 5.05it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.97it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 5.02it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.98it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 5.02it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.98it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:01, 5.01it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 4.98it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 4.99it/s][A
62%|██████▎ | 15/24 [00:03<00:01, 4.98it/s]
Total progress: 67%|██████▋ | 16/24 [00:03<00:01, 4.99it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.96it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 4.97it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.96it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 4.98it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.96it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 4.96it/s][A
79%|███████▉ | 19/24 [00:03<00:01, 4.96it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 4.97it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 4.95it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 4.95it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 4.95it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 4.95it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.96it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.96it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.96it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.96it/s][A
100%|██████████| 24/24 [00:04<00:00, 4.96it/s]
100%|██████████| 24/24 [00:04<00:00, 4.98it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 5318.06 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 5318.06 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 4134.50 MB, All loaded to GPU.
Moving model(s) has taken 0.06 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.96it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.76it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 5156.63 MB ... Unload model JointTextEncoder Current free memory is 6915.49 MB ... Unload model KModel Current free memory is 11915.88 MB ... Unload model IntegratedAutoencoderKL Done.
################################################################
[1m[32mInstall script for stable-diffusion + Web UI
[1m[34mTested on Debian 11 (Bullseye), Fedora 34+ and openSUSE Leap 15.4 or newer.[0m
################################################################
################################################################
Running on [1m[32mroot[0m user
################################################################
################################################################
Repo already cloned, using it as install directory
################################################################
################################################################
Create and activate python venv
################################################################
################################################################
Launching launch.py...
################################################################
glibc version is 2.39
Check TCMalloc: libtcmalloc_minimal.so.4
libtcmalloc_minimal.so.4 is linked with libc.so,execute LD_PRELOAD=/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4
=============================================================================================
INCOMPATIBLE PYTHON VERSION
This program is tested with 3.10.6 Python, but you have 3.12.3.
If you encounter an error with "RuntimeError: Couldn't install torch." message,
or any other error regarding unsuccessful package (library) installation,
please downgrade (or upgrade) to the latest version of 3.10 Python
and delete current Python and "venv" folder in WebUI's directory.
You can download 3.10 Python from here: https://www.python.org/downloads/release/python-3106/
Use --skip-python-version-check to suppress this warning.
=============================================================================================
Python 3.12.3 (main, Jan 22 2026, 20:57:42) [GCC 13.3.0]
Version: f2.0.1v1.10.1-previous-669-gdfdcbab6
Commit hash: dfdcbab685e57677014f05a3309b48cc87383167
Legacy Preprocessor init warning: Unable to install insightface automatically. Please try run `pip install insightface` manually.
Launching Web UI with arguments: -f --listen --api --enable-insecure-extension-access --xformers --no-half-vae --port 7887
Total VRAM 20017 MB, total RAM 64105 MB
pytorch version: 2.3.1+cu121
WARNING:xformers:A matching Triton is not available, some optimizations will not be enabled
Traceback (most recent call last):
File "/opt/sd-webui/venv/lib/python3.12/site-packages/xformers/__init__.py", line 57, in _is_triton_available
import triton # noqa
^^^^^^^^^^^^^
ModuleNotFoundError: No module named 'triton'
xformers version: 0.0.27
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA RTX 4000 SFF Ada Generation : native
Hint: your device supports --cuda-malloc for potential speed improvements.
VAE dtype preferences: [torch.bfloat16, torch.float32] -> torch.bfloat16
CUDA Using Stream: False
Using xformers cross attention
Using xformers attention for VAE
ControlNet preprocessor location: /opt/sd-webui/models/ControlNetPreprocessor
*** Error loading script: soft_inpainting.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 525, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/sd-webui/modules/script_loading.py", line 13, in load_module
module_spec.loader.exec_module(module)
File "<frozen importlib._bootstrap_external>", line 995, in exec_module
File "<frozen importlib._bootstrap>", line 488, in _call_with_frames_removed
File "/opt/sd-webui/extensions-builtin/soft-inpainting/scripts/soft_inpainting.py", line 10, in <module>
from joblib import Parallel, delayed, cpu_count
ModuleNotFoundError: No module named 'joblib'
---
2026-02-27 09:16:10,796 - ControlNet - [0;32mINFO[0m - ControlNet UI callback registered.
Model selected: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
Using online LoRAs in FP16: False
Running on local URL: http://0.0.0.0:7887
Thanks for being a Gradio user! If you have questions or feedback, please join our Discord server and chat with us: https://discord.gg/feTf9x3ZSB
To create a public link, set `share=True` in `launch()`.
Loading Model: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Done.
Startup time: 9.3s (prepare environment: 1.8s, launcher: 0.2s, import torch: 3.7s, other imports: 0.2s, load scripts: 0.8s, create ui: 1.1s, gradio launch: 0.5s, add APIs: 0.9s).
StateDict Keys: {'unet': 1680, 'vae': 248, 'text_encoder': 197, 'text_encoder_2': 518, 'ignore': 0}
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
K-Model Created: {'storage_dtype': torch.float16, 'computation_dtype': torch.float16}
Model loaded in 1.6s (unload existing model: 0.1s, forge model load: 1.5s).
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
*** Error running process: /opt/sd-webui/extensions-builtin/sd_forge_neveroom/scripts/forge_never_oom.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 844, in process
script.process(p, *script_args)
File "/opt/sd-webui/extensions-builtin/sd_forge_neveroom/scripts/forge_never_oom.py", line 27, in process
unet_enabled, vae_enabled = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 2, got 0)
---
[Unload] Trying to free 3051.58 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 12152.08 MB, Model Require: 1559.68 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 9568.41 MB, All loaded to GPU.
Moving model(s) has taken 0.97 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 10348.38 MB ... Done.
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_dynamic_thresholding/scripts/forge_dynamic_thresholding.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_dynamic_thresholding/scripts/forge_dynamic_thresholding.py", line 49, in process_before_every_sampling
enabled, mimic_scale, threshold_percentile, mimic_mode, mimic_scale_min, cfg_mode, cfg_scale_min, \
ValueError: not enough values to unpack (expected 12, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_freeu/scripts/forge_freeu.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_freeu/scripts/forge_freeu.py", line 143, in process_before_every_sampling
freeu_enabled, freeu_b1, freeu_b2, freeu_s1, freeu_s2, freeu_start, freeu_end = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 7, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_kohya_hrfix/scripts/kohya_hrfix.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_kohya_hrfix/scripts/kohya_hrfix.py", line 79, in process_before_every_sampling
enabled, block_number, downscale_factor, start_percent, end_percent, downscale_after_skip, downscale_method, upscale_method = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 8, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_latent_modifier/scripts/forge_latent_modifier.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_latent_modifier/scripts/forge_latent_modifier.py", line 96, in process_before_every_sampling
enabled, sharpness_multiplier, sharpness_method, tonemap_multiplier, tonemap_method, tonemap_percentile, contrast_multiplier, combat_method, combat_cfg_drift, rescale_cfg_phi, extra_noise_type, extra_noise_method, extra_noise_multiplier, extra_noise_lowpass, divisive_norm_size, divisive_norm_multiplier, spectral_mod_mode, spectral_mod_percentile, spectral_mod_multiplier, affect_uncond, dyn_cfg_augmentation = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 21, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_multidiffusion/scripts/forge_multidiffusion.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_multidiffusion/scripts/forge_multidiffusion.py", line 36, in process_before_every_sampling
enabled, method, tile_width, tile_height, tile_overlap, tile_batch_size = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 6, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_perturbed_attention/scripts/forge_perturbed_attention.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_perturbed_attention/scripts/forge_perturbed_attention.py", line 50, in process_before_every_sampling
enabled, scale, attenuation, start_step, end_step = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 5, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_sag/scripts/forge_sag.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_sag/scripts/forge_sag.py", line 197, in process_before_every_sampling
enabled, scale, blur_sigma, threshold = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 4, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_stylealign/scripts/forge_stylealign.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_stylealign/scripts/forge_stylealign.py", line 33, in process_before_every_sampling
shared_attention, strength = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 2, got 0)
---
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 10347.63 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 10347.63 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 4426.58 MB, All loaded to GPU.
Moving model(s) has taken 3.26 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
4%|▍ | 1/24 [00:00<00:10, 2.14it/s]
8%|▊ | 2/24 [00:00<00:06, 3.25it/s]
Total progress: 12%|█▎ | 3/24 [00:00<00:02, 10.31it/s][A
12%|█▎ | 3/24 [00:00<00:05, 3.88it/s]
17%|█▋ | 4/24 [00:01<00:04, 4.26it/s]
Total progress: 21%|██ | 5/24 [00:00<00:02, 6.80it/s][A
21%|██ | 5/24 [00:01<00:04, 4.50it/s]
Total progress: 25%|██▌ | 6/24 [00:00<00:02, 6.22it/s][A
25%|██▌ | 6/24 [00:01<00:03, 4.67it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:02, 5.85it/s][A
29%|██▉ | 7/24 [00:01<00:03, 4.78it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:02, 5.60it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.86it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.43it/s][A
38%|███▊ | 9/24 [00:02<00:03, 4.89it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.29it/s][A
42%|████▏ | 10/24 [00:02<00:02, 4.93it/s]
Total progress: 46%|████▌ | 11/24 [00:01<00:02, 5.20it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.96it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 5.16it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.98it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 5.12it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.99it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:01, 5.09it/s][A
58%|█████▊ | 14/24 [00:03<00:02, 4.99it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 5.05it/s][A
62%|██████▎ | 15/24 [00:03<00:01, 4.99it/s]
Total progress: 67%|██████▋ | 16/24 [00:02<00:01, 5.04it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 5.00it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 5.04it/s][A
71%|███████ | 17/24 [00:03<00:01, 5.01it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 5.03it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 5.01it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:00, 5.02it/s][A
79%|███████▉ | 19/24 [00:04<00:00, 5.01it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 5.01it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 5.00it/s]
Total progress: 88%|████████▊ | 21/24 [00:03<00:00, 5.01it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 5.01it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 5.02it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 5.00it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 5.00it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.98it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.99it/s][A
100%|██████████| 24/24 [00:05<00:00, 5.00it/s]
100%|██████████| 24/24 [00:05<00:00, 4.75it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 5330.01 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 5330.01 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 4146.45 MB, All loaded to GPU.
Moving model(s) has taken 0.06 seconds
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.99it/s][A
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.84it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 5160.58 MB ... Unload model JointTextEncoder Current free memory is 6920.94 MB ... Unload model KModel Current free memory is 11918.28 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 12079.84 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 9302.87 MB, All loaded to GPU.
Moving model(s) has taken 0.60 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 10320.38 MB ... Done.
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 10319.62 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 10319.62 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 4398.57 MB, All loaded to GPU.
Moving model(s) has taken 1.67 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
Total progress: 8%|▊ | 2/24 [00:00<00:02, 10.05it/s][A
8%|▊ | 2/24 [00:00<00:04, 5.18it/s]
12%|█▎ | 3/24 [00:00<00:04, 5.11it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 6.33it/s][A
17%|█▋ | 4/24 [00:00<00:03, 5.07it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.86it/s][A
21%|██ | 5/24 [00:00<00:03, 5.04it/s]
Total progress: 25%|██▌ | 6/24 [00:00<00:03, 5.58it/s][A
25%|██▌ | 6/24 [00:01<00:03, 5.02it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.38it/s][A
29%|██▉ | 7/24 [00:01<00:03, 5.01it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.26it/s][A
33%|███▎ | 8/24 [00:01<00:03, 5.00it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.18it/s][A
38%|███▊ | 9/24 [00:01<00:02, 5.01it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.13it/s][A
42%|████▏ | 10/24 [00:01<00:02, 5.00it/s]
Total progress: 46%|████▌ | 11/24 [00:01<00:02, 5.08it/s][A
46%|████▌ | 11/24 [00:02<00:02, 5.01it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 5.06it/s][A
50%|█████ | 12/24 [00:02<00:02, 5.00it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 5.04it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.99it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:01, 5.02it/s][A
58%|█████▊ | 14/24 [00:02<00:01, 5.00it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 5.02it/s][A
62%|██████▎ | 15/24 [00:02<00:01, 4.99it/s]
Total progress: 67%|██████▋ | 16/24 [00:02<00:01, 5.01it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 5.00it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 5.01it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.99it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 5.00it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.99it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 4.99it/s][A
79%|███████▉ | 19/24 [00:03<00:00, 5.00it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 5.00it/s][A
83%|████████▎ | 20/24 [00:03<00:00, 4.99it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 4.99it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 4.98it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 4.99it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.99it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.99it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.99it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.99it/s][A
100%|██████████| 24/24 [00:04<00:00, 4.98it/s]
100%|██████████| 24/24 [00:04<00:00, 5.01it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 5320.46 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 5320.46 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 4136.90 MB, All loaded to GPU.
Moving model(s) has taken 0.06 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.99it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.79it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 5159.03 MB ... Unload model JointTextEncoder Current free memory is 6917.89 MB ... Unload model KModel Current free memory is 11918.28 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 12079.84 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 9302.87 MB, All loaded to GPU.
Moving model(s) has taken 0.59 seconds
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 10320.23 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 10320.23 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 4399.19 MB, All loaded to GPU.
Moving model(s) has taken 1.66 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
Total progress: 8%|▊ | 2/24 [00:00<00:02, 9.96it/s][A
8%|▊ | 2/24 [00:00<00:04, 5.10it/s]
Total progress: 12%|█▎ | 3/24 [00:00<00:02, 7.02it/s][A
12%|█▎ | 3/24 [00:00<00:04, 5.04it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 6.08it/s][A
17%|█▋ | 4/24 [00:00<00:03, 5.00it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.63it/s][A
21%|██ | 5/24 [00:00<00:03, 4.99it/s]
Total progress: 25%|██▌ | 6/24 [00:01<00:03, 5.39it/s][A
25%|██▌ | 6/24 [00:01<00:03, 4.98it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.24it/s][A
29%|██▉ | 7/24 [00:01<00:03, 4.97it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.14it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.96it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.07it/s][A
38%|███▊ | 9/24 [00:01<00:03, 4.95it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.03it/s][A
42%|████▏ | 10/24 [00:02<00:02, 4.97it/s]
Total progress: 46%|████▌ | 11/24 [00:02<00:02, 5.03it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.98it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 5.03it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.99it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 5.02it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.98it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:01, 5.00it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 4.99it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 5.01it/s][A
62%|██████▎ | 15/24 [00:03<00:01, 5.00it/s]
Total progress: 67%|██████▋ | 16/24 [00:03<00:01, 5.01it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 5.00it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 5.01it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.99it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 4.99it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 5.00it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:00, 5.01it/s][A
79%|███████▉ | 19/24 [00:03<00:00, 5.00it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 5.00it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 5.00it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 5.00it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 5.01it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 5.01it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 5.01it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 5.02it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 5.01it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 5.00it/s][A
100%|██████████| 24/24 [00:04<00:00, 5.00it/s]
100%|██████████| 24/24 [00:04<00:00, 4.99it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 5319.57 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 5319.57 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 4136.01 MB, All loaded to GPU.
Moving model(s) has taken 0.06 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 5.00it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.77it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 5158.14 MB ... Unload model JointTextEncoder Current free memory is 6917.00 MB ... Unload model KModel Current free memory is 11917.38 MB ... Unload model IntegratedAutoencoderKL Done.
################################################################
[1m[32mInstall script for stable-diffusion + Web UI
[1m[34mTested on Debian 11 (Bullseye), Fedora 34+ and openSUSE Leap 15.4 or newer.[0m
################################################################
################################################################
Running on [1m[32mroot[0m user
################################################################
################################################################
Repo already cloned, using it as install directory
################################################################
################################################################
Create and activate python venv
################################################################
################################################################
Launching launch.py...
################################################################
glibc version is 2.39
Check TCMalloc: libtcmalloc_minimal.so.4
libtcmalloc_minimal.so.4 is linked with libc.so,execute LD_PRELOAD=/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4
=============================================================================================
INCOMPATIBLE PYTHON VERSION
This program is tested with 3.10.6 Python, but you have 3.12.3.
If you encounter an error with "RuntimeError: Couldn't install torch." message,
or any other error regarding unsuccessful package (library) installation,
please downgrade (or upgrade) to the latest version of 3.10 Python
and delete current Python and "venv" folder in WebUI's directory.
You can download 3.10 Python from here: https://www.python.org/downloads/release/python-3106/
Use --skip-python-version-check to suppress this warning.
=============================================================================================
Python 3.12.3 (main, Jan 22 2026, 20:57:42) [GCC 13.3.0]
Version: f2.0.1v1.10.1-previous-669-gdfdcbab6
Commit hash: dfdcbab685e57677014f05a3309b48cc87383167
Legacy Preprocessor init warning: Unable to install insightface automatically. Please try run `pip install insightface` manually.
Launching Web UI with arguments: -f --listen --api --enable-insecure-extension-access --xformers --no-half-vae --port 7887
Total VRAM 20017 MB, total RAM 64105 MB
pytorch version: 2.3.1+cu121
WARNING:xformers:A matching Triton is not available, some optimizations will not be enabled
Traceback (most recent call last):
File "/opt/sd-webui/venv/lib/python3.12/site-packages/xformers/__init__.py", line 57, in _is_triton_available
import triton # noqa
^^^^^^^^^^^^^
ModuleNotFoundError: No module named 'triton'
xformers version: 0.0.27
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA RTX 4000 SFF Ada Generation : native
Hint: your device supports --cuda-malloc for potential speed improvements.
VAE dtype preferences: [torch.bfloat16, torch.float32] -> torch.bfloat16
CUDA Using Stream: False
Using xformers cross attention
Using xformers attention for VAE
ControlNet preprocessor location: /opt/sd-webui/models/ControlNetPreprocessor
*** Error loading script: soft_inpainting.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 525, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/sd-webui/modules/script_loading.py", line 13, in load_module
module_spec.loader.exec_module(module)
File "<frozen importlib._bootstrap_external>", line 995, in exec_module
File "<frozen importlib._bootstrap>", line 488, in _call_with_frames_removed
File "/opt/sd-webui/extensions-builtin/soft-inpainting/scripts/soft_inpainting.py", line 10, in <module>
from joblib import Parallel, delayed, cpu_count
ModuleNotFoundError: No module named 'joblib'
---
2026-02-27 17:15:22,538 - ControlNet - [0;32mINFO[0m - ControlNet UI callback registered.
Model selected: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
Using online LoRAs in FP16: False
Running on local URL: http://0.0.0.0:7887
To create a public link, set `share=True` in `launch()`.
Loading Model: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Done.
Startup time: 24.8s (prepare environment: 3.4s, launcher: 0.5s, import torch: 9.3s, initialize shared: 0.2s, other imports: 0.5s, load scripts: 3.3s, create ui: 4.1s, gradio launch: 1.6s, add APIs: 2.0s).
StateDict Keys: {'unet': 1680, 'vae': 248, 'text_encoder': 197, 'text_encoder_2': 518, 'ignore': 0}
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
K-Model Created: {'storage_dtype': torch.float16, 'computation_dtype': torch.float16}
Model loaded in 3.0s (unload existing model: 0.3s, forge model load: 2.7s).
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
*** Error running process: /opt/sd-webui/extensions-builtin/sd_forge_neveroom/scripts/forge_never_oom.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 844, in process
script.process(p, *script_args)
File "/opt/sd-webui/extensions-builtin/sd_forge_neveroom/scripts/forge_never_oom.py", line 27, in process
unet_enabled, vae_enabled = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 2, got 0)
---
[Unload] Trying to free 3051.58 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 11912.96 MB, Model Require: 1559.68 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 9329.28 MB, All loaded to GPU.
Moving model(s) has taken 1.21 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 10109.26 MB ... Done.
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_dynamic_thresholding/scripts/forge_dynamic_thresholding.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_dynamic_thresholding/scripts/forge_dynamic_thresholding.py", line 49, in process_before_every_sampling
enabled, mimic_scale, threshold_percentile, mimic_mode, mimic_scale_min, cfg_mode, cfg_scale_min, \
ValueError: not enough values to unpack (expected 12, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_freeu/scripts/forge_freeu.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_freeu/scripts/forge_freeu.py", line 143, in process_before_every_sampling
freeu_enabled, freeu_b1, freeu_b2, freeu_s1, freeu_s2, freeu_start, freeu_end = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 7, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_kohya_hrfix/scripts/kohya_hrfix.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_kohya_hrfix/scripts/kohya_hrfix.py", line 79, in process_before_every_sampling
enabled, block_number, downscale_factor, start_percent, end_percent, downscale_after_skip, downscale_method, upscale_method = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 8, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_latent_modifier/scripts/forge_latent_modifier.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_latent_modifier/scripts/forge_latent_modifier.py", line 96, in process_before_every_sampling
enabled, sharpness_multiplier, sharpness_method, tonemap_multiplier, tonemap_method, tonemap_percentile, contrast_multiplier, combat_method, combat_cfg_drift, rescale_cfg_phi, extra_noise_type, extra_noise_method, extra_noise_multiplier, extra_noise_lowpass, divisive_norm_size, divisive_norm_multiplier, spectral_mod_mode, spectral_mod_percentile, spectral_mod_multiplier, affect_uncond, dyn_cfg_augmentation = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 21, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_multidiffusion/scripts/forge_multidiffusion.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_multidiffusion/scripts/forge_multidiffusion.py", line 36, in process_before_every_sampling
enabled, method, tile_width, tile_height, tile_overlap, tile_batch_size = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 6, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_perturbed_attention/scripts/forge_perturbed_attention.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_perturbed_attention/scripts/forge_perturbed_attention.py", line 50, in process_before_every_sampling
enabled, scale, attenuation, start_step, end_step = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 5, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_sag/scripts/forge_sag.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_sag/scripts/forge_sag.py", line 197, in process_before_every_sampling
enabled, scale, blur_sigma, threshold = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 4, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_stylealign/scripts/forge_stylealign.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_stylealign/scripts/forge_stylealign.py", line 33, in process_before_every_sampling
shared_attention, strength = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 2, got 0)
---
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 10108.50 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 10108.50 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 4187.46 MB, All loaded to GPU.
Moving model(s) has taken 4.04 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
4%|▍ | 1/24 [00:00<00:12, 1.82it/s]
8%|▊ | 2/24 [00:00<00:07, 2.91it/s]
Total progress: 12%|█▎ | 3/24 [00:00<00:02, 10.09it/s][A
12%|█▎ | 3/24 [00:00<00:05, 3.60it/s]
17%|█▋ | 4/24 [00:01<00:04, 4.05it/s]
Total progress: 21%|██ | 5/24 [00:00<00:02, 6.77it/s][A
21%|██ | 5/24 [00:01<00:04, 4.35it/s]
Total progress: 25%|██▌ | 6/24 [00:00<00:03, 5.77it/s][A
25%|██▌ | 6/24 [00:01<00:03, 4.55it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.59it/s][A
29%|██▉ | 7/24 [00:01<00:03, 4.67it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.32it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.74it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.23it/s][A
38%|███▊ | 9/24 [00:02<00:03, 4.83it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.14it/s][A
42%|████▏ | 10/24 [00:02<00:02, 4.87it/s]
Total progress: 46%|████▌ | 11/24 [00:01<00:02, 5.08it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.90it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 4.92it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.93it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 4.82it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.94it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:02, 4.63it/s][A
58%|█████▊ | 14/24 [00:03<00:02, 4.81it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 4.60it/s][A
62%|██████▎ | 15/24 [00:03<00:01, 4.67it/s]
Total progress: 67%|██████▋ | 16/24 [00:03<00:01, 4.70it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.75it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 4.75it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.74it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 4.67it/s][A
75%|███████▌ | 18/24 [00:04<00:01, 4.71it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 4.79it/s][A
79%|███████▉ | 19/24 [00:04<00:01, 4.75it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 4.85it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 4.78it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 4.89it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 4.85it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 5.06it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.85it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.73it/s][A
96%|█████████▌| 23/24 [00:05<00:00, 4.85it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.99it/s][A
100%|██████████| 24/24 [00:05<00:00, 4.88it/s]
100%|██████████| 24/24 [00:05<00:00, 4.56it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 5090.88 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 5090.88 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3907.33 MB, All loaded to GPU.
Moving model(s) has taken 0.15 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.99it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.51it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4921.46 MB ... Unload model JointTextEncoder Current free memory is 6681.81 MB ... Unload model KModel Current free memory is 11679.15 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 11840.72 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 9063.74 MB, All loaded to GPU.
Moving model(s) has taken 1.72 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 10081.25 MB ... Done.
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 10080.50 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 10080.50 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 4159.45 MB, All loaded to GPU.
Moving model(s) has taken 4.90 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
4%|▍ | 1/24 [00:00<00:12, 1.79it/s]
Total progress: 8%|▊ | 2/24 [00:00<00:06, 3.53it/s][A
8%|▊ | 2/24 [00:01<00:12, 1.77it/s]
Total progress: 12%|█▎ | 3/24 [00:01<00:07, 2.63it/s][A
12%|█▎ | 3/24 [00:01<00:11, 1.84it/s]
Total progress: 17%|█▋ | 4/24 [00:01<00:07, 2.64it/s][A
17%|█▋ | 4/24 [00:02<00:09, 2.10it/s]
Total progress: 21%|██ | 5/24 [00:01<00:06, 2.77it/s][A
21%|██ | 5/24 [00:02<00:08, 2.37it/s]
Total progress: 25%|██▌ | 6/24 [00:02<00:06, 2.77it/s][A
25%|██▌ | 6/24 [00:02<00:07, 2.48it/s]
Total progress: 29%|██▉ | 7/24 [00:02<00:05, 2.94it/s][A
29%|██▉ | 7/24 [00:03<00:06, 2.73it/s]
Total progress: 33%|███▎ | 8/24 [00:02<00:05, 2.72it/s][A
33%|███▎ | 8/24 [00:03<00:06, 2.59it/s]
Total progress: 38%|███▊ | 9/24 [00:03<00:05, 2.57it/s][A
38%|███▊ | 9/24 [00:03<00:06, 2.49it/s]
Total progress: 42%|████▏ | 10/24 [00:03<00:05, 2.49it/s][A
42%|████▏ | 10/24 [00:04<00:05, 2.43it/s]
Total progress: 46%|████▌ | 11/24 [00:04<00:05, 2.48it/s][A
46%|████▌ | 11/24 [00:04<00:05, 2.44it/s]
Total progress: 50%|█████ | 12/24 [00:04<00:04, 2.68it/s][A
50%|█████ | 12/24 [00:05<00:04, 2.63it/s]
Total progress: 54%|█████▍ | 13/24 [00:04<00:03, 3.24it/s][A
54%|█████▍ | 13/24 [00:05<00:03, 3.07it/s]
Total progress: 58%|█████▊ | 14/24 [00:04<00:02, 3.64it/s][A
58%|█████▊ | 14/24 [00:05<00:02, 3.47it/s]
Total progress: 62%|██████▎ | 15/24 [00:05<00:02, 3.81it/s][A
62%|██████▎ | 15/24 [00:05<00:02, 3.79it/s]
Total progress: 67%|██████▋ | 16/24 [00:05<00:01, 4.16it/s][A
67%|██████▋ | 16/24 [00:05<00:01, 4.07it/s]
Total progress: 71%|███████ | 17/24 [00:05<00:01, 4.32it/s][A
71%|███████ | 17/24 [00:06<00:01, 4.30it/s]
Total progress: 75%|███████▌ | 18/24 [00:05<00:01, 4.47it/s][A
75%|███████▌ | 18/24 [00:06<00:01, 4.46it/s]
Total progress: 79%|███████▉ | 19/24 [00:05<00:01, 4.60it/s][A
79%|███████▉ | 19/24 [00:06<00:01, 4.60it/s]
Total progress: 83%|████████▎ | 20/24 [00:06<00:00, 4.63it/s][A
83%|████████▎ | 20/24 [00:06<00:00, 4.66it/s]
Total progress: 88%|████████▊ | 21/24 [00:06<00:00, 5.32it/s][A
88%|████████▊ | 21/24 [00:06<00:00, 4.75it/s]
Total progress: 92%|█████████▏| 22/24 [00:06<00:00, 5.04it/s][A
92%|█████████▏| 22/24 [00:07<00:00, 4.80it/s]
Total progress: 96%|█████████▌| 23/24 [00:06<00:00, 4.83it/s][A
96%|█████████▌| 23/24 [00:07<00:00, 4.84it/s]
Total progress: 100%|██████████| 24/24 [00:06<00:00, 4.97it/s][A
100%|██████████| 24/24 [00:07<00:00, 4.86it/s]
100%|██████████| 24/24 [00:07<00:00, 3.22it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 5079.83 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 5079.83 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3896.27 MB, All loaded to GPU.
Moving model(s) has taken 0.08 seconds
Total progress: 100%|██████████| 24/24 [00:07<00:00, 4.97it/s][A
Total progress: 100%|██████████| 24/24 [00:07<00:00, 3.31it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4918.40 MB ... Unload model JointTextEncoder Current free memory is 6677.26 MB ... Unload model KModel Current free memory is 11677.64 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 11839.21 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 9062.23 MB, All loaded to GPU.
Moving model(s) has taken 0.70 seconds
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 10079.60 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 10079.60 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 4158.55 MB, All loaded to GPU.
Moving model(s) has taken 1.97 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
4%|▍ | 1/24 [00:00<00:02, 9.09it/s]
Total progress: 8%|▊ | 2/24 [00:00<00:02, 10.76it/s][A
8%|▊ | 2/24 [00:00<00:04, 4.75it/s]
12%|█▎ | 3/24 [00:00<00:04, 4.84it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 6.37it/s][A
17%|█▋ | 4/24 [00:00<00:04, 4.87it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.94it/s][A
21%|██ | 5/24 [00:01<00:03, 4.88it/s]
Total progress: 25%|██▌ | 6/24 [00:00<00:03, 5.54it/s][A
25%|██▌ | 6/24 [00:01<00:03, 4.90it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.32it/s][A
29%|██▉ | 7/24 [00:01<00:03, 4.90it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.16it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.91it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.11it/s][A
38%|███▊ | 9/24 [00:01<00:03, 4.92it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.06it/s][A
42%|████▏ | 10/24 [00:02<00:02, 4.92it/s]
Total progress: 46%|████▌ | 11/24 [00:01<00:02, 5.12it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.92it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 5.02it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.93it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 5.05it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.95it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:01, 5.04it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 4.97it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 5.02it/s][A
62%|██████▎ | 15/24 [00:03<00:01, 4.97it/s]
Total progress: 67%|██████▋ | 16/24 [00:03<00:01, 5.01it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.96it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 4.98it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.95it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 4.97it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.96it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 4.97it/s][A
79%|███████▉ | 19/24 [00:03<00:01, 4.97it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 4.94it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 4.96it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 4.98it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 4.96it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 4.77it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.96it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.85it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.97it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.88it/s][A
100%|██████████| 24/24 [00:04<00:00, 4.99it/s]
100%|██████████| 24/24 [00:04<00:00, 4.97it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 5078.94 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 5078.94 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3895.38 MB, All loaded to GPU.
Moving model(s) has taken 0.08 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.88it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.74it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4917.51 MB ... Unload model JointTextEncoder Current free memory is 6676.36 MB ... Unload model KModel Current free memory is 11676.75 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 11838.32 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 9061.34 MB, All loaded to GPU.
Moving model(s) has taken 0.68 seconds
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 10078.71 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 10078.71 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 4157.66 MB, All loaded to GPU.
Moving model(s) has taken 1.81 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
Total progress: 8%|▊ | 2/24 [00:00<00:02, 9.99it/s][A
8%|▊ | 2/24 [00:00<00:04, 5.08it/s]
Total progress: 12%|█▎ | 3/24 [00:00<00:03, 7.00it/s][A
12%|█▎ | 3/24 [00:00<00:04, 5.02it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 6.07it/s][A
17%|█▋ | 4/24 [00:00<00:03, 5.00it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.64it/s][A
21%|██ | 5/24 [00:00<00:03, 5.00it/s]
Total progress: 25%|██▌ | 6/24 [00:01<00:03, 5.41it/s][A
25%|██▌ | 6/24 [00:01<00:03, 5.00it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.27it/s][A
29%|██▉ | 7/24 [00:01<00:03, 5.00it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.17it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.98it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.10it/s][A
38%|███▊ | 9/24 [00:01<00:03, 4.98it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.06it/s][A
42%|████▏ | 10/24 [00:02<00:02, 4.98it/s]
Total progress: 46%|████▌ | 11/24 [00:02<00:02, 5.05it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.99it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 5.03it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.98it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 5.01it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.99it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:01, 5.00it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 4.98it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 4.99it/s][A
62%|██████▎ | 15/24 [00:03<00:01, 4.98it/s]
Total progress: 67%|██████▋ | 16/24 [00:03<00:01, 4.99it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.97it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 4.97it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.97it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 4.97it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.96it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 4.97it/s][A
79%|███████▉ | 19/24 [00:03<00:01, 4.95it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 4.95it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 4.95it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 4.94it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 4.93it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 4.94it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.93it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.93it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.93it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.92it/s][A
100%|██████████| 24/24 [00:04<00:00, 4.92it/s]
100%|██████████| 24/24 [00:04<00:00, 4.97it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 5079.83 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 5079.83 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3896.27 MB, All loaded to GPU.
Moving model(s) has taken 0.07 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.92it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.72it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4918.40 MB ... Unload model JointTextEncoder Current free memory is 6677.26 MB ... Unload model KModel Current free memory is 11677.64 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 11839.21 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 9062.23 MB, All loaded to GPU.
Moving model(s) has taken 0.68 seconds
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 10079.60 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 10079.60 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 4158.55 MB, All loaded to GPU.
Moving model(s) has taken 1.94 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
4%|▍ | 1/24 [00:00<00:02, 9.45it/s]
Total progress: 8%|▊ | 2/24 [00:00<00:02, 10.06it/s][A
8%|▊ | 2/24 [00:00<00:04, 4.68it/s]
12%|█▎ | 3/24 [00:00<00:04, 4.80it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 6.41it/s][A
17%|█▋ | 4/24 [00:00<00:04, 4.85it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.95it/s][A
21%|██ | 5/24 [00:01<00:03, 4.90it/s]
Total progress: 25%|██▌ | 6/24 [00:00<00:03, 5.54it/s][A
25%|██▌ | 6/24 [00:01<00:03, 4.93it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.44it/s][A
29%|██▉ | 7/24 [00:01<00:03, 4.93it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.20it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.94it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.20it/s][A
38%|███▊ | 9/24 [00:01<00:03, 4.94it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.12it/s][A
42%|████▏ | 10/24 [00:02<00:02, 4.95it/s]
Total progress: 46%|████▌ | 11/24 [00:01<00:02, 5.07it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.94it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 4.99it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.93it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 4.99it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.92it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:02, 4.96it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 4.91it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 4.94it/s][A
62%|██████▎ | 15/24 [00:03<00:01, 4.91it/s]
Total progress: 67%|██████▋ | 16/24 [00:03<00:01, 4.94it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.91it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 4.93it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.91it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 4.91it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.90it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 4.89it/s][A
79%|███████▉ | 19/24 [00:03<00:01, 4.90it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 4.89it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 4.89it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 4.92it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 4.91it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 4.92it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.91it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.91it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.90it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.88it/s][A
100%|██████████| 24/24 [00:04<00:00, 4.90it/s]
100%|██████████| 24/24 [00:04<00:00, 4.93it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 5078.94 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 5078.94 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3895.38 MB, All loaded to GPU.
Moving model(s) has taken 0.07 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.88it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.71it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4917.51 MB ... Unload model JointTextEncoder Current free memory is 6676.36 MB ... Unload model KModel Current free memory is 11676.75 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 11838.32 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 9061.34 MB, All loaded to GPU.
Moving model(s) has taken 0.59 seconds
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 10078.71 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 10078.71 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 4157.66 MB, All loaded to GPU.
Moving model(s) has taken 1.68 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
Total progress: 8%|▊ | 2/24 [00:00<00:02, 9.90it/s][A
8%|▊ | 2/24 [00:00<00:04, 5.13it/s]
Total progress: 12%|█▎ | 3/24 [00:00<00:02, 7.07it/s][A
12%|█▎ | 3/24 [00:00<00:04, 5.10it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 6.15it/s][A
17%|█▋ | 4/24 [00:00<00:03, 5.06it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.69it/s][A
21%|██ | 5/24 [00:00<00:03, 5.00it/s]
Total progress: 25%|██▌ | 6/24 [00:01<00:03, 5.38it/s][A
25%|██▌ | 6/24 [00:01<00:03, 4.97it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.23it/s][A
29%|██▉ | 7/24 [00:01<00:03, 4.97it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.14it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.98it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.10it/s][A
38%|███▊ | 9/24 [00:01<00:03, 4.96it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.04it/s][A
42%|████▏ | 10/24 [00:02<00:02, 4.96it/s]
Total progress: 46%|████▌ | 11/24 [00:02<00:02, 5.02it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.97it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 5.00it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.96it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 4.99it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.95it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:02, 4.97it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 4.96it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 4.98it/s][A
62%|██████▎ | 15/24 [00:03<00:01, 4.96it/s]
Total progress: 67%|██████▋ | 16/24 [00:03<00:01, 4.96it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.94it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 4.94it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.94it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 4.94it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.93it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 4.92it/s][A
79%|███████▉ | 19/24 [00:03<00:01, 4.92it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 4.93it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 4.91it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 4.90it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 4.91it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 4.92it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.91it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.90it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.91it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.92it/s][A
100%|██████████| 24/24 [00:04<00:00, 4.90it/s]
100%|██████████| 24/24 [00:04<00:00, 4.95it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 5078.04 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 5078.04 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3894.48 MB, All loaded to GPU.
Moving model(s) has taken 0.06 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.92it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.73it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4916.61 MB ... Unload model JointTextEncoder Current free memory is 6675.47 MB ... Unload model KModel Current free memory is 11675.86 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 11837.42 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 9060.45 MB, All loaded to GPU.
Moving model(s) has taken 0.60 seconds
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 10077.81 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 10077.81 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 4156.77 MB, All loaded to GPU.
Moving model(s) has taken 1.69 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
Total progress: 8%|▊ | 2/24 [00:00<00:02, 9.82it/s][A
8%|▊ | 2/24 [00:00<00:04, 5.06it/s]
Total progress: 12%|█▎ | 3/24 [00:00<00:02, 7.01it/s][A
12%|█▎ | 3/24 [00:00<00:04, 5.03it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 6.08it/s][A
17%|█▋ | 4/24 [00:00<00:03, 5.00it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.63it/s][A
21%|██ | 5/24 [00:01<00:03, 4.98it/s]
Total progress: 25%|██▌ | 6/24 [00:01<00:03, 5.37it/s][A
25%|██▌ | 6/24 [00:01<00:03, 4.94it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 4.90it/s][A
29%|██▉ | 7/24 [00:01<00:03, 4.91it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 4.51it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.87it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:03, 4.52it/s][A
38%|███▊ | 9/24 [00:01<00:03, 4.81it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 4.79it/s][A
42%|████▏ | 10/24 [00:02<00:02, 4.76it/s]
Total progress: 46%|████▌ | 11/24 [00:02<00:02, 4.87it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.74it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 5.20it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.80it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 5.12it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.84it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:01, 5.07it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 4.88it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 5.03it/s][A
62%|██████▎ | 15/24 [00:03<00:01, 4.90it/s]
Total progress: 67%|██████▋ | 16/24 [00:03<00:01, 5.01it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.91it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 4.99it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.93it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 4.98it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.94it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 4.97it/s][A
79%|███████▉ | 19/24 [00:03<00:01, 4.94it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 4.97it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 4.93it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 4.94it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 4.93it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 4.94it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.92it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.92it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.92it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.93it/s][A
100%|██████████| 24/24 [00:04<00:00, 4.91it/s]
100%|██████████| 24/24 [00:04<00:00, 4.90it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 5077.15 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 5077.15 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3893.59 MB, All loaded to GPU.
Moving model(s) has taken 0.06 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.93it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.68it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4915.72 MB ... Unload model JointTextEncoder Current free memory is 6674.58 MB ... Unload model KModel Current free memory is 11674.96 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 11836.53 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 9059.55 MB, All loaded to GPU.
Moving model(s) has taken 0.66 seconds
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 10076.92 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 10076.92 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 4155.87 MB, All loaded to GPU.
Moving model(s) has taken 1.68 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
Total progress: 8%|▊ | 2/24 [00:00<00:02, 10.04it/s][A
8%|▊ | 2/24 [00:00<00:04, 5.26it/s]
12%|█▎ | 3/24 [00:00<00:04, 5.13it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 6.26it/s][A
17%|█▋ | 4/24 [00:00<00:03, 5.04it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.75it/s][A
21%|██ | 5/24 [00:00<00:03, 4.95it/s]
Total progress: 25%|██▌ | 6/24 [00:01<00:03, 5.46it/s][A
25%|██▌ | 6/24 [00:01<00:03, 4.93it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.27it/s][A
29%|██▉ | 7/24 [00:01<00:03, 4.93it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.17it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.94it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.10it/s][A
38%|███▊ | 9/24 [00:01<00:03, 4.92it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.03it/s][A
42%|████▏ | 10/24 [00:02<00:02, 4.91it/s]
Total progress: 46%|████▌ | 11/24 [00:02<00:02, 4.98it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.89it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 4.94it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.89it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 4.92it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.88it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:02, 4.90it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 4.90it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 4.92it/s][A
62%|██████▎ | 15/24 [00:03<00:01, 4.91it/s]
Total progress: 67%|██████▋ | 16/24 [00:03<00:01, 4.92it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.91it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 4.92it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.91it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 4.92it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.91it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 4.92it/s][A
79%|███████▉ | 19/24 [00:03<00:01, 4.90it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 4.89it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 4.90it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 4.90it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 4.89it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 4.88it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.89it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.90it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.88it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.88it/s][A
100%|██████████| 24/24 [00:04<00:00, 4.89it/s]
100%|██████████| 24/24 [00:04<00:00, 4.92it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 5078.94 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 5078.94 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3895.38 MB, All loaded to GPU.
Moving model(s) has taken 0.06 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.88it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.70it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4917.51 MB ... Unload model JointTextEncoder Current free memory is 6676.36 MB ... Unload model KModel Current free memory is 11676.75 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 11838.32 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 9061.34 MB, All loaded to GPU.
Moving model(s) has taken 0.60 seconds
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 10078.71 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 10078.71 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 4157.66 MB, All loaded to GPU.
Moving model(s) has taken 1.67 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
Total progress: 8%|▊ | 2/24 [00:00<00:02, 9.92it/s][A
8%|▊ | 2/24 [00:00<00:04, 5.16it/s]
Total progress: 12%|█▎ | 3/24 [00:00<00:02, 7.00it/s][A
12%|█▎ | 3/24 [00:00<00:04, 5.03it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 6.02it/s][A
17%|█▋ | 4/24 [00:00<00:03, 5.00it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.59it/s][A
21%|██ | 5/24 [00:01<00:03, 4.93it/s]
Total progress: 25%|██▌ | 6/24 [00:01<00:03, 5.31it/s][A
25%|██▌ | 6/24 [00:01<00:03, 4.94it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.19it/s][A
29%|██▉ | 7/24 [00:01<00:03, 4.92it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.08it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.90it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.00it/s][A
38%|███▊ | 9/24 [00:01<00:03, 4.88it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 4.96it/s][A
42%|████▏ | 10/24 [00:02<00:02, 4.90it/s]
Total progress: 46%|████▌ | 11/24 [00:02<00:02, 4.96it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.91it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 4.96it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.92it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 4.95it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.92it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:02, 4.94it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 4.91it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 4.92it/s][A
62%|██████▎ | 15/24 [00:03<00:01, 4.91it/s]
Total progress: 67%|██████▋ | 16/24 [00:03<00:01, 4.92it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.91it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 4.92it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.91it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 4.91it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.91it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 4.92it/s][A
79%|███████▉ | 19/24 [00:03<00:01, 4.90it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 4.89it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 4.90it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 4.91it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 4.91it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 4.92it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.92it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.92it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.90it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.89it/s][A
100%|██████████| 24/24 [00:04<00:00, 4.89it/s]
100%|██████████| 24/24 [00:04<00:00, 4.92it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 5078.04 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 5078.04 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3894.48 MB, All loaded to GPU.
Moving model(s) has taken 0.06 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.89it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.70it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4916.61 MB ... Unload model JointTextEncoder Current free memory is 6675.47 MB ... Unload model KModel Current free memory is 11675.86 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 11837.42 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 9060.45 MB, All loaded to GPU.
Moving model(s) has taken 0.59 seconds
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 10077.81 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 10077.81 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 4156.77 MB, All loaded to GPU.
Moving model(s) has taken 1.66 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
Total progress: 8%|▊ | 2/24 [00:00<00:02, 9.74it/s][A
8%|▊ | 2/24 [00:00<00:04, 5.06it/s]
Total progress: 12%|█▎ | 3/24 [00:00<00:03, 6.95it/s][A
12%|█▎ | 3/24 [00:00<00:04, 5.01it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 6.04it/s][A
17%|█▋ | 4/24 [00:00<00:04, 4.97it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.57it/s][A
21%|██ | 5/24 [00:01<00:03, 4.93it/s]
Total progress: 25%|██▌ | 6/24 [00:01<00:03, 5.33it/s][A
25%|██▌ | 6/24 [00:01<00:03, 4.92it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.17it/s][A
29%|██▉ | 7/24 [00:01<00:03, 4.91it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.09it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.91it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.04it/s][A
38%|███▊ | 9/24 [00:01<00:03, 4.90it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 4.97it/s][A
42%|████▏ | 10/24 [00:02<00:02, 4.89it/s]
Total progress: 46%|████▌ | 11/24 [00:02<00:02, 4.96it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.90it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 4.93it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.90it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 4.92it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.90it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:02, 4.93it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 4.91it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 4.92it/s][A
62%|██████▎ | 15/24 [00:03<00:01, 4.89it/s]
Total progress: 67%|██████▋ | 16/24 [00:03<00:01, 4.89it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.89it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 4.89it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.89it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 4.90it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.88it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 4.88it/s][A
79%|███████▉ | 19/24 [00:03<00:01, 4.89it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 4.89it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 4.89it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 4.90it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 4.90it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 4.90it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.91it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.90it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.89it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.89it/s][A
100%|██████████| 24/24 [00:04<00:00, 4.89it/s]
100%|██████████| 24/24 [00:04<00:00, 4.91it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 5077.15 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 5077.15 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3893.59 MB, All loaded to GPU.
Moving model(s) has taken 0.06 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.89it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.68it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4915.72 MB ... Unload model JointTextEncoder Current free memory is 6674.58 MB ... Unload model KModel Current free memory is 11674.96 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 11836.53 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 9059.55 MB, All loaded to GPU.
Moving model(s) has taken 0.59 seconds
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 10076.92 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 10076.92 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 4155.87 MB, All loaded to GPU.
Moving model(s) has taken 1.70 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
Total progress: 8%|▊ | 2/24 [00:00<00:02, 9.84it/s][A
8%|▊ | 2/24 [00:00<00:04, 5.01it/s]
Total progress: 12%|█▎ | 3/24 [00:00<00:03, 6.90it/s][A
12%|█▎ | 3/24 [00:00<00:04, 4.97it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 6.01it/s][A
17%|█▋ | 4/24 [00:00<00:04, 4.95it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.53it/s][A
21%|██ | 5/24 [00:01<00:03, 4.89it/s]
Total progress: 25%|██▌ | 6/24 [00:01<00:03, 5.30it/s][A
25%|██▌ | 6/24 [00:01<00:03, 4.89it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.14it/s][A
29%|██▉ | 7/24 [00:01<00:03, 4.89it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.06it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.89it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.01it/s][A
38%|███▊ | 9/24 [00:01<00:03, 4.90it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 4.98it/s][A
42%|████▏ | 10/24 [00:02<00:02, 4.90it/s]
Total progress: 46%|████▌ | 11/24 [00:02<00:02, 4.96it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.90it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 4.94it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.89it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 4.92it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.89it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:02, 4.91it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 4.88it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 4.90it/s][A
62%|██████▎ | 15/24 [00:03<00:01, 4.86it/s]
Total progress: 67%|██████▋ | 16/24 [00:03<00:01, 4.86it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.86it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 4.87it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.87it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 4.87it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.87it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 4.87it/s][A
79%|███████▉ | 19/24 [00:03<00:01, 4.87it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 4.87it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 4.87it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 4.88it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 4.88it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 4.88it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.88it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.88it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.87it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.87it/s][A
100%|██████████| 24/24 [00:04<00:00, 4.88it/s]
100%|██████████| 24/24 [00:04<00:00, 4.89it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 5076.25 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 5076.25 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3892.70 MB, All loaded to GPU.
Moving model(s) has taken 0.06 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.87it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.68it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4914.83 MB ... Unload model JointTextEncoder Current free memory is 6673.68 MB ... Unload model KModel Current free memory is 11674.07 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 11835.64 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 9058.66 MB, All loaded to GPU.
Moving model(s) has taken 0.60 seconds
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 10076.03 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 10076.03 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 4154.98 MB, All loaded to GPU.
Moving model(s) has taken 1.66 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
Total progress: 8%|▊ | 2/24 [00:00<00:02, 9.74it/s][A
8%|▊ | 2/24 [00:00<00:04, 5.05it/s]
Total progress: 12%|█▎ | 3/24 [00:00<00:03, 6.93it/s][A
12%|█▎ | 3/24 [00:00<00:04, 4.99it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 6.02it/s][A
17%|█▋ | 4/24 [00:00<00:04, 4.97it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.57it/s][A
21%|██ | 5/24 [00:01<00:03, 4.91it/s]
Total progress: 25%|██▌ | 6/24 [00:01<00:03, 5.30it/s][A
25%|██▌ | 6/24 [00:01<00:03, 4.91it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.18it/s][A
29%|██▉ | 7/24 [00:01<00:03, 4.92it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.09it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.92it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.03it/s][A
38%|███▊ | 9/24 [00:01<00:03, 4.91it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 4.99it/s][A
42%|████▏ | 10/24 [00:02<00:02, 4.89it/s]
Total progress: 46%|████▌ | 11/24 [00:02<00:02, 4.94it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.89it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 4.93it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.89it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 4.92it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.89it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:02, 4.91it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 4.88it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 4.89it/s][A
62%|██████▎ | 15/24 [00:03<00:01, 4.87it/s]
Total progress: 67%|██████▋ | 16/24 [00:03<00:01, 4.87it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.87it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 4.88it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.87it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 4.87it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.84it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 4.84it/s][A
79%|███████▉ | 19/24 [00:03<00:01, 4.85it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 4.85it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 4.85it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 4.85it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 4.85it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 4.85it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.86it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.86it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.86it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.86it/s][A
100%|██████████| 24/24 [00:04<00:00, 4.86it/s]
100%|██████████| 24/24 [00:04<00:00, 4.89it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 5078.04 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 5078.04 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3894.48 MB, All loaded to GPU.
Moving model(s) has taken 0.06 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.86it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.67it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4916.61 MB ... Unload model JointTextEncoder Current free memory is 6675.47 MB ... Unload model KModel Current free memory is 11675.86 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 11837.42 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 9060.45 MB, All loaded to GPU.
Moving model(s) has taken 0.60 seconds
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 10077.81 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 10077.81 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 4156.77 MB, All loaded to GPU.
Moving model(s) has taken 1.69 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
Total progress: 8%|▊ | 2/24 [00:00<00:02, 9.89it/s][A
8%|▊ | 2/24 [00:00<00:04, 5.08it/s]
Total progress: 12%|█▎ | 3/24 [00:00<00:03, 6.95it/s][A
12%|█▎ | 3/24 [00:00<00:04, 5.01it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 6.02it/s][A
17%|█▋ | 4/24 [00:00<00:04, 4.97it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.55it/s][A
21%|██ | 5/24 [00:01<00:03, 4.90it/s]
Total progress: 25%|██▌ | 6/24 [00:01<00:03, 5.29it/s][A
25%|██▌ | 6/24 [00:01<00:03, 4.89it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.15it/s][A
29%|██▉ | 7/24 [00:01<00:03, 4.89it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.07it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.88it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:03, 4.98it/s][A
38%|███▊ | 9/24 [00:01<00:03, 4.86it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 4.94it/s][A
42%|████▏ | 10/24 [00:02<00:02, 4.86it/s]
Total progress: 46%|████▌ | 11/24 [00:02<00:02, 4.92it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.86it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 4.90it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.86it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 4.89it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.87it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:02, 4.88it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 4.86it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 4.87it/s][A
62%|██████▎ | 15/24 [00:03<00:01, 4.86it/s]
Total progress: 67%|██████▋ | 16/24 [00:03<00:01, 4.86it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.86it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 4.86it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.86it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 4.86it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.86it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 4.86it/s][A
79%|███████▉ | 19/24 [00:03<00:01, 4.85it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 4.85it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 4.84it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 4.84it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 4.84it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 4.85it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.84it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.84it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.84it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.84it/s][A
100%|██████████| 24/24 [00:04<00:00, 4.84it/s]
100%|██████████| 24/24 [00:04<00:00, 4.87it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 5077.15 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 5077.15 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3893.59 MB, All loaded to GPU.
Moving model(s) has taken 0.06 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.84it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.66it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4915.72 MB ... Unload model JointTextEncoder Current free memory is 6674.58 MB ... Unload model KModel Current free memory is 11674.96 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 11836.53 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 9059.55 MB, All loaded to GPU.
Moving model(s) has taken 0.60 seconds
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 10076.92 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 10076.92 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 4155.87 MB, All loaded to GPU.
Moving model(s) has taken 1.66 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
Total progress: 8%|▊ | 2/24 [00:00<00:02, 9.68it/s][A
8%|▊ | 2/24 [00:00<00:04, 5.00it/s]
Total progress: 12%|█▎ | 3/24 [00:00<00:03, 6.91it/s][A
12%|█▎ | 3/24 [00:00<00:04, 4.93it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 5.93it/s][A
17%|█▋ | 4/24 [00:00<00:04, 4.91it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.51it/s][A
21%|██ | 5/24 [00:01<00:03, 4.88it/s]
Total progress: 25%|██▌ | 6/24 [00:01<00:03, 5.29it/s][A
25%|██▌ | 6/24 [00:01<00:03, 4.89it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.15it/s][A
29%|██▉ | 7/24 [00:01<00:03, 4.89it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.06it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.89it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.00it/s][A
38%|███▊ | 9/24 [00:01<00:03, 4.88it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 4.96it/s][A
42%|████▏ | 10/24 [00:02<00:02, 4.87it/s]
Total progress: 46%|████▌ | 11/24 [00:02<00:02, 4.93it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.87it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 4.91it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.87it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 4.89it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.86it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:02, 4.89it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 4.86it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 4.87it/s][A
62%|██████▎ | 15/24 [00:03<00:01, 4.86it/s]
Total progress: 67%|██████▋ | 16/24 [00:03<00:01, 4.86it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.85it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 4.86it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.86it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 4.86it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.86it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 4.86it/s][A
79%|███████▉ | 19/24 [00:03<00:01, 4.86it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 4.86it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 4.84it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 4.85it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 4.84it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 4.84it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.84it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.84it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.84it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.84it/s][A
100%|██████████| 24/24 [00:04<00:00, 4.84it/s]
100%|██████████| 24/24 [00:04<00:00, 4.87it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 5076.25 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 5076.25 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3892.70 MB, All loaded to GPU.
Moving model(s) has taken 0.06 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.84it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.66it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4914.83 MB ... Unload model JointTextEncoder Current free memory is 6673.68 MB ... Unload model KModel Current free memory is 11674.07 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 11835.64 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 9058.66 MB, All loaded to GPU.
Moving model(s) has taken 0.59 seconds
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 10076.03 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 10076.03 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 4154.98 MB, All loaded to GPU.
Moving model(s) has taken 1.66 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
Total progress: 8%|▊ | 2/24 [00:00<00:02, 9.70it/s][A
8%|▊ | 2/24 [00:00<00:04, 5.00it/s]
Total progress: 12%|█▎ | 3/24 [00:00<00:03, 6.89it/s][A
12%|█▎ | 3/24 [00:00<00:04, 4.96it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 6.00it/s][A
17%|█▋ | 4/24 [00:00<00:04, 4.95it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.56it/s][A
21%|██ | 5/24 [00:01<00:03, 4.90it/s]
Total progress: 25%|██▌ | 6/24 [00:01<00:03, 5.29it/s][A
25%|██▌ | 6/24 [00:01<00:03, 4.89it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.16it/s][A
29%|██▉ | 7/24 [00:01<00:03, 4.89it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.06it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.89it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.01it/s][A
38%|███▊ | 9/24 [00:01<00:03, 4.88it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 4.97it/s][A
42%|████▏ | 10/24 [00:02<00:02, 4.88it/s]
Total progress: 46%|████▌ | 11/24 [00:02<00:02, 4.94it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.89it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 4.92it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.88it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 4.91it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.88it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:02, 4.89it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 4.87it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 4.88it/s][A
62%|██████▎ | 15/24 [00:03<00:01, 4.87it/s]
Total progress: 67%|██████▋ | 16/24 [00:03<00:01, 4.88it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.87it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 4.88it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.86it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 4.87it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.86it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 4.86it/s][A
79%|███████▉ | 19/24 [00:03<00:01, 4.86it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 4.86it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 4.86it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 4.86it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 4.86it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 4.86it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.85it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.85it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.85it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.85it/s][A
100%|██████████| 24/24 [00:04<00:00, 4.85it/s]
100%|██████████| 24/24 [00:04<00:00, 4.88it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 5075.36 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 5075.36 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3891.80 MB, All loaded to GPU.
Moving model(s) has taken 0.06 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.85it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.66it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4913.93 MB ... Unload model JointTextEncoder Current free memory is 6672.79 MB ... Unload model KModel Current free memory is 11673.17 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 11834.74 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 9057.76 MB, All loaded to GPU.
Moving model(s) has taken 0.61 seconds
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 10075.13 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 10075.13 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 4154.08 MB, All loaded to GPU.
Moving model(s) has taken 1.68 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
Total progress: 8%|▊ | 2/24 [00:00<00:02, 9.89it/s][A
8%|▊ | 2/24 [00:00<00:04, 5.04it/s]
Total progress: 12%|█▎ | 3/24 [00:00<00:03, 6.96it/s][A
12%|█▎ | 3/24 [00:00<00:04, 4.99it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 6.00it/s][A
17%|█▋ | 4/24 [00:00<00:04, 4.94it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.54it/s][A
21%|██ | 5/24 [00:01<00:03, 4.88it/s]
Total progress: 25%|██▌ | 6/24 [00:01<00:03, 5.28it/s][A
25%|██▌ | 6/24 [00:01<00:03, 4.88it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.15it/s][A
29%|██▉ | 7/24 [00:01<00:03, 4.88it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.05it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.88it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:03, 4.99it/s][A
38%|███▊ | 9/24 [00:01<00:03, 4.87it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 4.95it/s][A
42%|████▏ | 10/24 [00:02<00:02, 4.86it/s]
Total progress: 46%|████▌ | 11/24 [00:02<00:02, 4.92it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.86it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 4.90it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.87it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 4.89it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.86it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:02, 4.89it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 4.87it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 4.88it/s][A
62%|██████▎ | 15/24 [00:03<00:01, 4.86it/s]
Total progress: 67%|██████▋ | 16/24 [00:03<00:01, 4.86it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.85it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 4.86it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.85it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 4.85it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.85it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 4.85it/s][A
79%|███████▉ | 19/24 [00:03<00:01, 4.85it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 4.86it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 4.85it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 4.85it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 4.84it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 4.84it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.84it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.85it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.85it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.85it/s][A
100%|██████████| 24/24 [00:04<00:00, 4.85it/s]
100%|██████████| 24/24 [00:04<00:00, 4.87it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 5077.15 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 5077.15 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3893.59 MB, All loaded to GPU.
Moving model(s) has taken 0.06 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.85it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.66it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4915.72 MB ... Unload model JointTextEncoder Current free memory is 6674.58 MB ... Unload model KModel Current free memory is 11674.96 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 11836.53 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 9059.55 MB, All loaded to GPU.
Moving model(s) has taken 0.59 seconds
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 10076.92 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 10076.92 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 4155.87 MB, All loaded to GPU.
Moving model(s) has taken 1.68 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
Total progress: 8%|▊ | 2/24 [00:00<00:02, 9.74it/s][A
8%|▊ | 2/24 [00:00<00:04, 5.00it/s]
Total progress: 12%|█▎ | 3/24 [00:00<00:03, 6.91it/s][A
12%|█▎ | 3/24 [00:00<00:04, 4.95it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 5.98it/s][A
17%|█▋ | 4/24 [00:00<00:04, 4.92it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.53it/s][A
21%|██ | 5/24 [00:01<00:03, 4.88it/s]
Total progress: 25%|██▌ | 6/24 [00:01<00:03, 5.28it/s][A
25%|██▌ | 6/24 [00:01<00:03, 4.88it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.14it/s][A
29%|██▉ | 7/24 [00:01<00:03, 4.88it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.05it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.87it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:03, 4.99it/s][A
38%|███▊ | 9/24 [00:01<00:03, 4.86it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 4.94it/s][A
42%|████▏ | 10/24 [00:02<00:02, 4.85it/s]
Total progress: 46%|████▌ | 11/24 [00:02<00:02, 4.91it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.85it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 4.89it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.85it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 4.88it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.85it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:02, 4.87it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 4.85it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 4.86it/s][A
62%|██████▎ | 15/24 [00:03<00:01, 4.84it/s]
Total progress: 67%|██████▋ | 16/24 [00:03<00:01, 4.85it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.84it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 4.84it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.84it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 4.84it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.83it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 4.84it/s][A
79%|███████▉ | 19/24 [00:03<00:01, 4.84it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 4.84it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 4.83it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 4.83it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 4.83it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 4.83it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.83it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.84it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.84it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.84it/s][A
100%|██████████| 24/24 [00:04<00:00, 4.83it/s]
100%|██████████| 24/24 [00:04<00:00, 4.86it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 5076.25 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 5076.25 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3892.70 MB, All loaded to GPU.
Moving model(s) has taken 0.06 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.84it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.65it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4914.83 MB ... Unload model JointTextEncoder Current free memory is 6673.68 MB ... Unload model KModel Current free memory is 11674.07 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 11835.64 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 9058.66 MB, All loaded to GPU.
Moving model(s) has taken 0.60 seconds
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 10076.03 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 10076.03 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 4154.98 MB, All loaded to GPU.
Moving model(s) has taken 1.68 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
Total progress: 8%|▊ | 2/24 [00:00<00:02, 9.93it/s][A
8%|▊ | 2/24 [00:00<00:04, 5.02it/s]
Total progress: 12%|█▎ | 3/24 [00:00<00:03, 6.88it/s][A
12%|█▎ | 3/24 [00:00<00:04, 4.95it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 5.97it/s][A
17%|█▋ | 4/24 [00:00<00:04, 4.93it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.52it/s][A
21%|██ | 5/24 [00:01<00:03, 4.87it/s]
Total progress: 25%|██▌ | 6/24 [00:01<00:03, 5.28it/s][A
25%|██▌ | 6/24 [00:01<00:03, 4.88it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.14it/s][A
29%|██▉ | 7/24 [00:01<00:03, 4.88it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.06it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.87it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:03, 4.99it/s][A
38%|███▊ | 9/24 [00:01<00:03, 4.87it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 4.95it/s][A
42%|████▏ | 10/24 [00:02<00:02, 4.86it/s]
Total progress: 46%|████▌ | 11/24 [00:02<00:02, 4.92it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.87it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 4.91it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.87it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 4.89it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.86it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:02, 4.87it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 4.85it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 4.86it/s][A
62%|██████▎ | 15/24 [00:03<00:01, 4.85it/s]
Total progress: 67%|██████▋ | 16/24 [00:03<00:01, 4.86it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.85it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 4.85it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.84it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 4.84it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.84it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 4.85it/s][A
79%|███████▉ | 19/24 [00:03<00:01, 4.84it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 4.84it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 4.84it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 4.84it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 4.83it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 4.83it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.83it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.83it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.83it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.83it/s][A
100%|██████████| 24/24 [00:04<00:00, 4.82it/s]
100%|██████████| 24/24 [00:04<00:00, 4.86it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 5075.36 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 5075.36 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3891.80 MB, All loaded to GPU.
Moving model(s) has taken 0.06 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.83it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.65it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4913.93 MB ... Unload model JointTextEncoder Current free memory is 6672.79 MB ... Unload model KModel Current free memory is 11673.17 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 11834.74 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 9057.76 MB, All loaded to GPU.
Moving model(s) has taken 0.59 seconds
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 10075.13 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 10075.13 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 4154.08 MB, All loaded to GPU.
Moving model(s) has taken 1.67 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
Total progress: 8%|▊ | 2/24 [00:00<00:02, 9.71it/s][A
8%|▊ | 2/24 [00:00<00:04, 5.00it/s]
Total progress: 12%|█▎ | 3/24 [00:00<00:03, 6.91it/s][A
12%|█▎ | 3/24 [00:00<00:04, 4.95it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 5.98it/s][A
17%|█▋ | 4/24 [00:00<00:04, 4.92it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.53it/s][A
21%|██ | 5/24 [00:01<00:03, 4.88it/s]
Total progress: 25%|██▌ | 6/24 [00:01<00:03, 5.28it/s][A
25%|██▌ | 6/24 [00:01<00:03, 4.88it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.14it/s][A
29%|██▉ | 7/24 [00:01<00:03, 4.87it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.04it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.86it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:03, 4.98it/s][A
38%|███▊ | 9/24 [00:01<00:03, 4.86it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 4.93it/s][A
42%|████▏ | 10/24 [00:02<00:02, 4.84it/s]
Total progress: 46%|████▌ | 11/24 [00:02<00:02, 4.90it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.83it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 4.87it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.83it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 4.86it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.83it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:02, 4.85it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 4.83it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 4.84it/s][A
62%|██████▎ | 15/24 [00:03<00:01, 4.83it/s]
Total progress: 67%|██████▋ | 16/24 [00:03<00:01, 4.84it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.83it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 4.84it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.83it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 4.83it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.83it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 4.83it/s][A
79%|███████▉ | 19/24 [00:03<00:01, 4.82it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 4.82it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 4.82it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 4.82it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 4.82it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 4.82it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.82it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.82it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.83it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.83it/s][A
100%|██████████| 24/24 [00:04<00:00, 4.82it/s]
100%|██████████| 24/24 [00:04<00:00, 4.85it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 5074.47 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 5074.47 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3890.91 MB, All loaded to GPU.
Moving model(s) has taken 0.06 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.83it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.64it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4913.04 MB ... Unload model JointTextEncoder Current free memory is 6671.89 MB ... Unload model KModel Current free memory is 11672.28 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 11833.85 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 9056.87 MB, All loaded to GPU.
Moving model(s) has taken 0.59 seconds
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 10074.24 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 10074.24 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 4153.19 MB, All loaded to GPU.
Moving model(s) has taken 1.66 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
Total progress: 8%|▊ | 2/24 [00:00<00:02, 9.66it/s][A
8%|▊ | 2/24 [00:00<00:04, 5.00it/s]
Total progress: 12%|█▎ | 3/24 [00:00<00:03, 6.88it/s][A
12%|█▎ | 3/24 [00:00<00:04, 4.94it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 5.95it/s][A
17%|█▋ | 4/24 [00:00<00:04, 4.91it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.49it/s][A
21%|██ | 5/24 [00:01<00:03, 4.85it/s]
Total progress: 25%|██▌ | 6/24 [00:01<00:03, 5.24it/s][A
25%|██▌ | 6/24 [00:01<00:03, 4.85it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.11it/s][A
29%|██▉ | 7/24 [00:01<00:03, 4.86it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.03it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.86it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:03, 4.97it/s][A
38%|███▊ | 9/24 [00:01<00:03, 4.85it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 4.93it/s][A
42%|████▏ | 10/24 [00:02<00:02, 4.84it/s]
Total progress: 46%|████▌ | 11/24 [00:02<00:02, 4.90it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.84it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 4.89it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.85it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 4.87it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.85it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:02, 4.86it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 4.84it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 4.85it/s][A
62%|██████▎ | 15/24 [00:03<00:01, 4.83it/s]
Total progress: 67%|██████▋ | 16/24 [00:03<00:01, 4.84it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.83it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 4.84it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.83it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 4.83it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.82it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 4.83it/s][A
79%|███████▉ | 19/24 [00:03<00:01, 4.83it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 4.83it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 4.82it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 4.83it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 4.82it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 4.83it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.83it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.83it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.83it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.82it/s][A
100%|██████████| 24/24 [00:04<00:00, 4.82it/s]
100%|██████████| 24/24 [00:04<00:00, 4.85it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 5076.25 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 5076.25 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3892.70 MB, All loaded to GPU.
Moving model(s) has taken 0.06 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.82it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.64it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4914.83 MB ... Unload model JointTextEncoder Current free memory is 6673.68 MB ... Unload model KModel Current free memory is 11674.07 MB ... Unload model IntegratedAutoencoderKL Done.
################################################################
[1m[32mInstall script for stable-diffusion + Web UI
[1m[34mTested on Debian 11 (Bullseye), Fedora 34+ and openSUSE Leap 15.4 or newer.[0m
################################################################
################################################################
Running on [1m[32mroot[0m user
################################################################
################################################################
Repo already cloned, using it as install directory
################################################################
################################################################
Create and activate python venv
################################################################
################################################################
Launching launch.py...
################################################################
glibc version is 2.39
Check TCMalloc: libtcmalloc_minimal.so.4
libtcmalloc_minimal.so.4 is linked with libc.so,execute LD_PRELOAD=/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4
=============================================================================================
INCOMPATIBLE PYTHON VERSION
This program is tested with 3.10.6 Python, but you have 3.12.3.
If you encounter an error with "RuntimeError: Couldn't install torch." message,
or any other error regarding unsuccessful package (library) installation,
please downgrade (or upgrade) to the latest version of 3.10 Python
and delete current Python and "venv" folder in WebUI's directory.
You can download 3.10 Python from here: https://www.python.org/downloads/release/python-3106/
Use --skip-python-version-check to suppress this warning.
=============================================================================================
Python 3.12.3 (main, Jan 22 2026, 20:57:42) [GCC 13.3.0]
Version: f2.0.1v1.10.1-previous-669-gdfdcbab6
Commit hash: dfdcbab685e57677014f05a3309b48cc87383167
Legacy Preprocessor init warning: Unable to install insightface automatically. Please try run `pip install insightface` manually.
Launching Web UI with arguments: -f --listen --api --enable-insecure-extension-access --xformers --no-half-vae --port 7887
Total VRAM 20017 MB, total RAM 64105 MB
pytorch version: 2.3.1+cu121
WARNING:xformers:A matching Triton is not available, some optimizations will not be enabled
Traceback (most recent call last):
File "/opt/sd-webui/venv/lib/python3.12/site-packages/xformers/__init__.py", line 57, in _is_triton_available
import triton # noqa
^^^^^^^^^^^^^
ModuleNotFoundError: No module named 'triton'
xformers version: 0.0.27
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA RTX 4000 SFF Ada Generation : native
Hint: your device supports --cuda-malloc for potential speed improvements.
VAE dtype preferences: [torch.bfloat16, torch.float32] -> torch.bfloat16
CUDA Using Stream: False
Using xformers cross attention
Using xformers attention for VAE
ControlNet preprocessor location: /opt/sd-webui/models/ControlNetPreprocessor
*** Error loading script: soft_inpainting.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 525, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/sd-webui/modules/script_loading.py", line 13, in load_module
module_spec.loader.exec_module(module)
File "<frozen importlib._bootstrap_external>", line 995, in exec_module
File "<frozen importlib._bootstrap>", line 488, in _call_with_frames_removed
File "/opt/sd-webui/extensions-builtin/soft-inpainting/scripts/soft_inpainting.py", line 10, in <module>
from joblib import Parallel, delayed, cpu_count
ModuleNotFoundError: No module named 'joblib'
---
2026-02-27 17:25:58,551 - ControlNet - [0;32mINFO[0m - ControlNet UI callback registered.
Model selected: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
Using online LoRAs in FP16: False
Running on local URL: http://0.0.0.0:7887
To create a public link, set `share=True` in `launch()`.
Loading Model: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Done.
Startup time: 8.1s (prepare environment: 1.2s, launcher: 0.2s, import torch: 3.2s, load scripts: 0.8s, create ui: 1.1s, gradio launch: 0.5s, add APIs: 0.9s).
StateDict Keys: {'unet': 1680, 'vae': 248, 'text_encoder': 197, 'text_encoder_2': 518, 'ignore': 0}
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
K-Model Created: {'storage_dtype': torch.float16, 'computation_dtype': torch.float16}
Model loaded in 0.9s (unload existing model: 0.1s, forge model load: 0.8s).
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
*** Error running process: /opt/sd-webui/extensions-builtin/sd_forge_neveroom/scripts/forge_never_oom.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 844, in process
script.process(p, *script_args)
File "/opt/sd-webui/extensions-builtin/sd_forge_neveroom/scripts/forge_never_oom.py", line 27, in process
unet_enabled, vae_enabled = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 2, got 0)
---
[Unload] Trying to free 3051.58 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 11912.96 MB, Model Require: 1559.68 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 9329.28 MB, All loaded to GPU.
Moving model(s) has taken 0.54 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 10109.26 MB ... Done.
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_dynamic_thresholding/scripts/forge_dynamic_thresholding.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_dynamic_thresholding/scripts/forge_dynamic_thresholding.py", line 49, in process_before_every_sampling
enabled, mimic_scale, threshold_percentile, mimic_mode, mimic_scale_min, cfg_mode, cfg_scale_min, \
ValueError: not enough values to unpack (expected 12, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_freeu/scripts/forge_freeu.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_freeu/scripts/forge_freeu.py", line 143, in process_before_every_sampling
freeu_enabled, freeu_b1, freeu_b2, freeu_s1, freeu_s2, freeu_start, freeu_end = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 7, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_kohya_hrfix/scripts/kohya_hrfix.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_kohya_hrfix/scripts/kohya_hrfix.py", line 79, in process_before_every_sampling
enabled, block_number, downscale_factor, start_percent, end_percent, downscale_after_skip, downscale_method, upscale_method = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 8, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_latent_modifier/scripts/forge_latent_modifier.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_latent_modifier/scripts/forge_latent_modifier.py", line 96, in process_before_every_sampling
enabled, sharpness_multiplier, sharpness_method, tonemap_multiplier, tonemap_method, tonemap_percentile, contrast_multiplier, combat_method, combat_cfg_drift, rescale_cfg_phi, extra_noise_type, extra_noise_method, extra_noise_multiplier, extra_noise_lowpass, divisive_norm_size, divisive_norm_multiplier, spectral_mod_mode, spectral_mod_percentile, spectral_mod_multiplier, affect_uncond, dyn_cfg_augmentation = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 21, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_multidiffusion/scripts/forge_multidiffusion.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_multidiffusion/scripts/forge_multidiffusion.py", line 36, in process_before_every_sampling
enabled, method, tile_width, tile_height, tile_overlap, tile_batch_size = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 6, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_perturbed_attention/scripts/forge_perturbed_attention.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_perturbed_attention/scripts/forge_perturbed_attention.py", line 50, in process_before_every_sampling
enabled, scale, attenuation, start_step, end_step = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 5, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_sag/scripts/forge_sag.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_sag/scripts/forge_sag.py", line 197, in process_before_every_sampling
enabled, scale, blur_sigma, threshold = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 4, got 0)
---
*** Error running process_before_every_sampling: /opt/sd-webui/extensions-builtin/sd_forge_stylealign/scripts/forge_stylealign.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 892, in process_before_every_sampling
script.process_before_every_sampling(p, *script_args, **kwargs)
File "/opt/sd-webui/extensions-builtin/sd_forge_stylealign/scripts/forge_stylealign.py", line 33, in process_before_every_sampling
shared_attention, strength = script_args
^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 2, got 0)
---
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 10108.50 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 10108.50 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 4187.46 MB, All loaded to GPU.
Moving model(s) has taken 1.83 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
4%|▍ | 1/24 [00:00<00:06, 3.73it/s]
8%|▊ | 2/24 [00:00<00:04, 4.46it/s]
Total progress: 12%|█▎ | 3/24 [00:00<00:02, 10.47it/s][A
12%|█▎ | 3/24 [00:00<00:04, 4.70it/s]
17%|█▋ | 4/24 [00:00<00:04, 4.82it/s]
Total progress: 21%|██ | 5/24 [00:00<00:02, 6.85it/s][A
21%|██ | 5/24 [00:01<00:03, 4.89it/s]
Total progress: 25%|██▌ | 6/24 [00:00<00:02, 6.26it/s][A
25%|██▌ | 6/24 [00:01<00:03, 4.92it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:02, 5.85it/s][A
29%|██▉ | 7/24 [00:01<00:03, 4.95it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:02, 5.58it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.97it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.42it/s][A
38%|███▊ | 9/24 [00:01<00:03, 5.00it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.30it/s][A
42%|████▏ | 10/24 [00:02<00:02, 5.01it/s]
Total progress: 46%|████▌ | 11/24 [00:01<00:02, 5.23it/s][A
46%|████▌ | 11/24 [00:02<00:02, 5.02it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 5.16it/s][A
50%|█████ | 12/24 [00:02<00:02, 5.02it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 5.12it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 5.01it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:01, 5.08it/s][A
58%|█████▊ | 14/24 [00:02<00:01, 5.00it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 5.05it/s][A
62%|██████▎ | 15/24 [00:03<00:01, 5.01it/s]
Total progress: 67%|██████▋ | 16/24 [00:02<00:01, 5.04it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 5.00it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 5.03it/s][A
71%|███████ | 17/24 [00:03<00:01, 5.01it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 5.03it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 5.02it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:00, 5.03it/s][A
79%|███████▉ | 19/24 [00:03<00:00, 5.00it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 5.01it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 5.00it/s]
Total progress: 88%|████████▊ | 21/24 [00:03<00:00, 5.01it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 5.01it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 5.00it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.99it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.99it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.99it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.99it/s][A
100%|██████████| 24/24 [00:04<00:00, 4.99it/s]
100%|██████████| 24/24 [00:04<00:00, 4.94it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 5090.88 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 5090.88 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3907.33 MB, All loaded to GPU.
Moving model(s) has taken 0.06 seconds
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.99it/s][A
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.88it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4921.46 MB ... Unload model JointTextEncoder Current free memory is 6681.81 MB ... Unload model KModel Current free memory is 11679.15 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 11840.72 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 9063.74 MB, All loaded to GPU.
Moving model(s) has taken 0.60 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 10081.25 MB ... Done.
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 10080.50 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 10080.50 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 4159.45 MB, All loaded to GPU.
Moving model(s) has taken 1.67 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
Total progress: 8%|▊ | 2/24 [00:00<00:02, 9.99it/s][A
8%|▊ | 2/24 [00:00<00:04, 5.14it/s]
Total progress: 12%|█▎ | 3/24 [00:00<00:02, 7.09it/s][A
12%|█▎ | 3/24 [00:00<00:04, 5.09it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 6.13it/s][A
17%|█▋ | 4/24 [00:00<00:03, 5.06it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.70it/s][A
21%|██ | 5/24 [00:00<00:03, 5.05it/s]
Total progress: 25%|██▌ | 6/24 [00:00<00:03, 5.45it/s][A
25%|██▌ | 6/24 [00:01<00:03, 5.04it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.30it/s][A
29%|██▉ | 7/24 [00:01<00:03, 5.02it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.21it/s][A
33%|███▎ | 8/24 [00:01<00:03, 5.03it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.16it/s][A
38%|███▊ | 9/24 [00:01<00:02, 5.04it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.12it/s][A
42%|████▏ | 10/24 [00:01<00:02, 5.03it/s]
Total progress: 46%|████▌ | 11/24 [00:01<00:02, 5.09it/s][A
46%|████▌ | 11/24 [00:02<00:02, 5.01it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 5.04it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.99it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 5.02it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.98it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:02, 5.00it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 4.97it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 4.99it/s][A
62%|██████▎ | 15/24 [00:02<00:01, 4.97it/s]
Total progress: 67%|██████▋ | 16/24 [00:03<00:01, 4.98it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.97it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 4.99it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.98it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 4.98it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.97it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 4.97it/s][A
79%|███████▉ | 19/24 [00:03<00:01, 4.97it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 4.97it/s][A
83%|████████▎ | 20/24 [00:03<00:00, 4.96it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 4.96it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 4.96it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 4.96it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.96it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.96it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.96it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.95it/s][A
100%|██████████| 24/24 [00:04<00:00, 4.95it/s]
100%|██████████| 24/24 [00:04<00:00, 4.99it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 5081.34 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 5081.34 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3897.78 MB, All loaded to GPU.
Moving model(s) has taken 0.06 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.95it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.77it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4919.91 MB ... Unload model JointTextEncoder Current free memory is 6678.76 MB ... Unload model KModel Current free memory is 11679.15 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 11840.72 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 9063.74 MB, All loaded to GPU.
Moving model(s) has taken 0.59 seconds
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 10081.11 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 10081.11 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 4160.06 MB, All loaded to GPU.
Moving model(s) has taken 1.67 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
Total progress: 8%|▊ | 2/24 [00:00<00:02, 9.92it/s][A
8%|▊ | 2/24 [00:00<00:04, 5.14it/s]
Total progress: 12%|█▎ | 3/24 [00:00<00:02, 7.09it/s][A
12%|█▎ | 3/24 [00:00<00:04, 5.09it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 6.12it/s][A
17%|█▋ | 4/24 [00:00<00:03, 5.04it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.67it/s][A
21%|██ | 5/24 [00:00<00:03, 5.02it/s]
Total progress: 25%|██▌ | 6/24 [00:01<00:03, 5.43it/s][A
25%|██▌ | 6/24 [00:01<00:03, 5.03it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.29it/s][A
29%|██▉ | 7/24 [00:01<00:03, 5.03it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.21it/s][A
33%|███▎ | 8/24 [00:01<00:03, 5.02it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.15it/s][A
38%|███▊ | 9/24 [00:01<00:02, 5.02it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.11it/s][A
42%|████▏ | 10/24 [00:01<00:02, 5.02it/s]
Total progress: 46%|████▌ | 11/24 [00:01<00:02, 5.08it/s][A
46%|████▌ | 11/24 [00:02<00:02, 5.02it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 5.06it/s][A
50%|█████ | 12/24 [00:02<00:02, 5.02it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 5.05it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 5.02it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:01, 5.04it/s][A
58%|█████▊ | 14/24 [00:02<00:01, 5.02it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 5.04it/s][A
62%|██████▎ | 15/24 [00:02<00:01, 5.02it/s]
Total progress: 67%|██████▋ | 16/24 [00:02<00:01, 5.03it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 5.03it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 5.04it/s][A
71%|███████ | 17/24 [00:03<00:01, 5.02it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 5.02it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 5.01it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:00, 5.01it/s][A
79%|███████▉ | 19/24 [00:03<00:00, 5.01it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 5.02it/s][A
83%|████████▎ | 20/24 [00:03<00:00, 5.02it/s]
Total progress: 88%|████████▊ | 21/24 [00:03<00:00, 5.02it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 5.01it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 5.01it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 5.01it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 5.01it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 5.01it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 5.01it/s][A
100%|██████████| 24/24 [00:04<00:00, 5.01it/s]
100%|██████████| 24/24 [00:04<00:00, 5.02it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 5080.44 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 5080.44 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 3896.89 MB, All loaded to GPU.
Moving model(s) has taken 0.06 seconds
Total progress: 100%|██████████| 24/24 [00:04<00:00, 5.01it/s][A
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.80it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 4919.01 MB ... Unload model JointTextEncoder Current free memory is 6677.87 MB ... Unload model KModel Current free memory is 11678.26 MB ... Unload model IntegratedAutoencoderKL Done.
################################################################
[1m[32mInstall script for stable-diffusion + Web UI
[1m[34mTested on Debian 11 (Bullseye), Fedora 34+ and openSUSE Leap 15.4 or newer.[0m
################################################################
################################################################
Running on [1m[32mroot[0m user
################################################################
################################################################
Repo already cloned, using it as install directory
################################################################
################################################################
Create and activate python venv
################################################################
################################################################
Launching launch.py...
################################################################
glibc version is 2.39
Check TCMalloc: libtcmalloc_minimal.so.4
libtcmalloc_minimal.so.4 is linked with libc.so,execute LD_PRELOAD=/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4
=============================================================================================
INCOMPATIBLE PYTHON VERSION
This program is tested with 3.10.6 Python, but you have 3.12.3.
If you encounter an error with "RuntimeError: Couldn't install torch." message,
or any other error regarding unsuccessful package (library) installation,
please downgrade (or upgrade) to the latest version of 3.10 Python
and delete current Python and "venv" folder in WebUI's directory.
You can download 3.10 Python from here: https://www.python.org/downloads/release/python-3106/
Use --skip-python-version-check to suppress this warning.
=============================================================================================
Python 3.12.3 (main, Jan 22 2026, 20:57:42) [GCC 13.3.0]
Version: f2.0.1v1.10.1-previous-669-gdfdcbab6
Commit hash: dfdcbab685e57677014f05a3309b48cc87383167
Legacy Preprocessor init warning: Unable to install insightface automatically. Please try run `pip install insightface` manually.
Launching Web UI with arguments: -f --listen --api --enable-insecure-extension-access --xformers --no-half-vae --port 7887
Total VRAM 20017 MB, total RAM 64105 MB
pytorch version: 2.3.1+cu121
WARNING:xformers:A matching Triton is not available, some optimizations will not be enabled
Traceback (most recent call last):
File "/opt/sd-webui/venv/lib/python3.12/site-packages/xformers/__init__.py", line 57, in _is_triton_available
import triton # noqa
^^^^^^^^^^^^^
ModuleNotFoundError: No module named 'triton'
xformers version: 0.0.27
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA RTX 4000 SFF Ada Generation : native
Hint: your device supports --cuda-malloc for potential speed improvements.
VAE dtype preferences: [torch.bfloat16, torch.float32] -> torch.bfloat16
CUDA Using Stream: False
Using xformers cross attention
Using xformers attention for VAE
ControlNet preprocessor location: /opt/sd-webui/models/ControlNetPreprocessor
*** Error loading script: soft_inpainting.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 525, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/sd-webui/modules/script_loading.py", line 13, in load_module
module_spec.loader.exec_module(module)
File "<frozen importlib._bootstrap_external>", line 995, in exec_module
File "<frozen importlib._bootstrap>", line 488, in _call_with_frames_removed
File "/opt/sd-webui/extensions-builtin/soft-inpainting/scripts/soft_inpainting.py", line 10, in <module>
from joblib import Parallel, delayed, cpu_count
ModuleNotFoundError: No module named 'joblib'
---
2026-02-27 20:11:40,076 - ControlNet - [0;32mINFO[0m - ControlNet UI callback registered.
Model selected: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
Using online LoRAs in FP16: False
Running on local URL: http://0.0.0.0:7887
To create a public link, set `share=True` in `launch()`.
Loading Model: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Done.
Startup time: 9.5s (prepare environment: 1.9s, launcher: 0.3s, import torch: 3.8s, other imports: 0.2s, load scripts: 0.8s, create ui: 1.1s, gradio launch: 0.5s, add APIs: 0.9s).
StateDict Keys: {'unet': 1680, 'vae': 248, 'text_encoder': 197, 'text_encoder_2': 518, 'ignore': 0}
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
K-Model Created: {'storage_dtype': torch.float16, 'computation_dtype': torch.float16}
Model loaded in 4.7s (unload existing model: 0.2s, forge model load: 4.5s).
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3051.58 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 12548.79 MB, Model Require: 1559.68 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 9965.11 MB, All loaded to GPU.
Moving model(s) has taken 1.22 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 10741.26 MB ... Done.
[Unload] Trying to free 2615.54 MB for cuda:0 with 0 models keep loaded ... Current free memory is 10740.50 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 10740.50 MB, Model Require: 0.00 MB, Previously Loaded: 4897.05 MB, Inference Require: 1024.00 MB, Remaining: 9716.50 MB, All loaded to GPU.
Moving model(s) has taken 0.01 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
4%|▍ | 1/24 [00:00<00:12, 1.79it/s]
8%|▊ | 2/24 [00:00<00:07, 2.89it/s]
Total progress: 12%|█▎ | 3/24 [00:00<00:02, 10.19it/s][A
12%|█▎ | 3/24 [00:00<00:05, 3.59it/s]
17%|█▋ | 4/24 [00:01<00:04, 4.05it/s]
Total progress: 21%|██ | 5/24 [00:00<00:02, 6.77it/s][A
21%|██ | 5/24 [00:01<00:04, 4.36it/s]
Total progress: 25%|██▌ | 6/24 [00:00<00:02, 6.21it/s][A
25%|██▌ | 6/24 [00:01<00:03, 4.56it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:02, 5.84it/s][A
29%|██▉ | 7/24 [00:01<00:03, 4.70it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:02, 5.59it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.80it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.41it/s][A
38%|███▊ | 9/24 [00:02<00:03, 4.86it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.29it/s][A
42%|████▏ | 10/24 [00:02<00:02, 4.91it/s]
Total progress: 46%|████▌ | 11/24 [00:01<00:02, 5.21it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.94it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 5.14it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.96it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 5.10it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.97it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:01, 5.07it/s][A
58%|█████▊ | 14/24 [00:03<00:02, 4.98it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 5.05it/s][A
62%|██████▎ | 15/24 [00:03<00:01, 4.98it/s]
Total progress: 67%|██████▋ | 16/24 [00:02<00:01, 5.03it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.99it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 5.02it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.99it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 5.01it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.99it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:00, 5.01it/s][A
79%|███████▉ | 19/24 [00:04<00:01, 4.99it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 5.00it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 4.98it/s]
Total progress: 88%|████████▊ | 21/24 [00:03<00:00, 4.99it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 4.97it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 4.98it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.99it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.99it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.99it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.99it/s][A
100%|██████████| 24/24 [00:05<00:00, 5.00it/s]
100%|██████████| 24/24 [00:05<00:00, 4.66it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 10720.21 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 10720.21 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 9536.65 MB, All loaded to GPU.
Moving model(s) has taken 0.06 seconds
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.99it/s][A
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.83it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 10550.78 MB ... Unload model JointTextEncoder Current free memory is 12314.97 MB ... Unload model KModel Current free memory is 17314.28 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 17475.84 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 14698.87 MB, All loaded to GPU.
Moving model(s) has taken 0.60 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 15717.88 MB ... Done.
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 15717.13 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 15717.13 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 9796.08 MB, All loaded to GPU.
Moving model(s) has taken 1.67 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
Total progress: 8%|▊ | 2/24 [00:00<00:02, 10.16it/s][A
8%|▊ | 2/24 [00:00<00:04, 5.27it/s]
12%|█▎ | 3/24 [00:00<00:04, 5.13it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 6.29it/s][A
17%|█▋ | 4/24 [00:00<00:03, 5.09it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.85it/s][A
21%|██ | 5/24 [00:00<00:03, 5.02it/s]
Total progress: 25%|██▌ | 6/24 [00:01<00:03, 5.54it/s][A
25%|██▌ | 6/24 [00:01<00:03, 5.01it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.37it/s][A
29%|██▉ | 7/24 [00:01<00:03, 5.00it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.24it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.99it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.16it/s][A
38%|███▊ | 9/24 [00:01<00:03, 4.99it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.11it/s][A
42%|████▏ | 10/24 [00:01<00:02, 4.99it/s]
Total progress: 46%|████▌ | 11/24 [00:02<00:02, 5.06it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.99it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 5.04it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.98it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 5.02it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.99it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:01, 5.01it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 4.99it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 5.00it/s][A
62%|██████▎ | 15/24 [00:02<00:01, 4.98it/s]
Total progress: 67%|██████▋ | 16/24 [00:03<00:01, 5.00it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.97it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 4.98it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.97it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 4.98it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.98it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 4.99it/s][A
79%|███████▉ | 19/24 [00:03<00:01, 4.96it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 4.96it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 4.95it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 4.96it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 4.95it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 4.96it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.95it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.95it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.94it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.95it/s][A
100%|██████████| 24/24 [00:04<00:00, 4.95it/s]
100%|██████████| 24/24 [00:04<00:00, 4.99it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 10716.46 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 10716.46 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 9532.90 MB, All loaded to GPU.
Moving model(s) has taken 0.06 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.95it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.76it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 10555.03 MB ... Unload model JointTextEncoder Current free memory is 12313.89 MB ... Unload model KModel Current free memory is 17314.28 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 17475.84 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 14698.87 MB, All loaded to GPU.
Moving model(s) has taken 0.60 seconds
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 15716.23 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 15716.23 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 9795.19 MB, All loaded to GPU.
Moving model(s) has taken 1.66 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
Total progress: 8%|▊ | 2/24 [00:00<00:02, 9.91it/s][A
8%|▊ | 2/24 [00:00<00:04, 5.09it/s]
Total progress: 12%|█▎ | 3/24 [00:00<00:03, 6.97it/s][A
12%|█▎ | 3/24 [00:00<00:04, 5.02it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 6.05it/s][A
17%|█▋ | 4/24 [00:00<00:03, 5.01it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.63it/s][A
21%|██ | 5/24 [00:00<00:03, 5.01it/s]
Total progress: 25%|██▌ | 6/24 [00:01<00:03, 5.41it/s][A
25%|██▌ | 6/24 [00:01<00:03, 5.01it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.28it/s][A
29%|██▉ | 7/24 [00:01<00:03, 5.01it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.19it/s][A
33%|███▎ | 8/24 [00:01<00:03, 5.01it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.13it/s][A
38%|███▊ | 9/24 [00:01<00:03, 4.99it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.07it/s][A
42%|████▏ | 10/24 [00:01<00:02, 4.99it/s]
Total progress: 46%|████▌ | 11/24 [00:02<00:02, 5.05it/s][A
46%|████▌ | 11/24 [00:02<00:02, 5.00it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 5.04it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.99it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 5.02it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.99it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:01, 5.01it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 4.98it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 4.99it/s][A
62%|██████▎ | 15/24 [00:03<00:01, 4.98it/s]
Total progress: 67%|██████▋ | 16/24 [00:03<00:01, 5.00it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.99it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 5.00it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.98it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 4.97it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.97it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 4.98it/s][A
79%|███████▉ | 19/24 [00:03<00:01, 4.97it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 4.98it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 4.97it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 4.97it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 4.96it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 4.96it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.96it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.96it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.96it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.96it/s][A
100%|██████████| 24/24 [00:04<00:00, 4.97it/s]
100%|██████████| 24/24 [00:04<00:00, 4.99it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 10715.57 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 10715.57 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 9532.01 MB, All loaded to GPU.
Moving model(s) has taken 0.06 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.96it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.77it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 10554.14 MB ... Unload model JointTextEncoder Current free memory is 12313.00 MB ... Unload model KModel Current free memory is 17313.38 MB ... Unload model IntegratedAutoencoderKL Done.
################################################################
[1m[32mInstall script for stable-diffusion + Web UI
[1m[34mTested on Debian 11 (Bullseye), Fedora 34+ and openSUSE Leap 15.4 or newer.[0m
################################################################
################################################################
Running on [1m[32mroot[0m user
################################################################
################################################################
Repo already cloned, using it as install directory
################################################################
################################################################
Create and activate python venv
################################################################
################################################################
Launching launch.py...
################################################################
glibc version is 2.39
Check TCMalloc: libtcmalloc_minimal.so.4
libtcmalloc_minimal.so.4 is linked with libc.so,execute LD_PRELOAD=/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4
=============================================================================================
INCOMPATIBLE PYTHON VERSION
This program is tested with 3.10.6 Python, but you have 3.12.3.
If you encounter an error with "RuntimeError: Couldn't install torch." message,
or any other error regarding unsuccessful package (library) installation,
please downgrade (or upgrade) to the latest version of 3.10 Python
and delete current Python and "venv" folder in WebUI's directory.
You can download 3.10 Python from here: https://www.python.org/downloads/release/python-3106/
Use --skip-python-version-check to suppress this warning.
=============================================================================================
Python 3.12.3 (main, Jan 22 2026, 20:57:42) [GCC 13.3.0]
Version: f2.0.1v1.10.1-previous-669-gdfdcbab6
Commit hash: dfdcbab685e57677014f05a3309b48cc87383167
Legacy Preprocessor init warning: Unable to install insightface automatically. Please try run `pip install insightface` manually.
Launching Web UI with arguments: -f --listen --api --enable-insecure-extension-access --xformers --no-half-vae --port 7887
Total VRAM 20017 MB, total RAM 64105 MB
pytorch version: 2.3.1+cu121
WARNING:xformers:A matching Triton is not available, some optimizations will not be enabled
Traceback (most recent call last):
File "/opt/sd-webui/venv/lib/python3.12/site-packages/xformers/__init__.py", line 57, in _is_triton_available
import triton # noqa
^^^^^^^^^^^^^
ModuleNotFoundError: No module named 'triton'
xformers version: 0.0.27
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA RTX 4000 SFF Ada Generation : native
Hint: your device supports --cuda-malloc for potential speed improvements.
VAE dtype preferences: [torch.bfloat16, torch.float32] -> torch.bfloat16
CUDA Using Stream: False
Using xformers cross attention
Using xformers attention for VAE
ControlNet preprocessor location: /opt/sd-webui/models/ControlNetPreprocessor
*** Error loading script: soft_inpainting.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 525, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/sd-webui/modules/script_loading.py", line 13, in load_module
module_spec.loader.exec_module(module)
File "<frozen importlib._bootstrap_external>", line 995, in exec_module
File "<frozen importlib._bootstrap>", line 488, in _call_with_frames_removed
File "/opt/sd-webui/extensions-builtin/soft-inpainting/scripts/soft_inpainting.py", line 10, in <module>
from joblib import Parallel, delayed, cpu_count
ModuleNotFoundError: No module named 'joblib'
---
2026-02-28 22:22:52,946 - ControlNet - [0;32mINFO[0m - ControlNet UI callback registered.
Model selected: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
Using online LoRAs in FP16: False
Running on local URL: http://0.0.0.0:7887
To create a public link, set `share=True` in `launch()`.
Loading Model: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Done.
Startup time: 9.3s (prepare environment: 1.8s, launcher: 0.2s, import torch: 3.8s, other imports: 0.2s, load scripts: 0.8s, create ui: 1.1s, gradio launch: 0.5s, add APIs: 0.9s).
StateDict Keys: {'unet': 1680, 'vae': 248, 'text_encoder': 197, 'text_encoder_2': 518, 'ignore': 0}
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
K-Model Created: {'storage_dtype': torch.float16, 'computation_dtype': torch.float16}
Model loaded in 1.3s (unload existing model: 0.1s, forge model load: 1.1s).
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3051.58 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 19829.21 MB, Model Require: 1559.68 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 17245.53 MB, All loaded to GPU.
Moving model(s) has taken 0.97 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 18025.51 MB ... Done.
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 18024.75 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 18024.75 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 12103.71 MB, All loaded to GPU.
Moving model(s) has taken 3.20 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
4%|▍ | 1/24 [00:00<00:10, 2.16it/s]
8%|▊ | 2/24 [00:00<00:06, 3.28it/s]
Total progress: 12%|█▎ | 3/24 [00:00<00:02, 10.39it/s][A
12%|█▎ | 3/24 [00:00<00:05, 3.89it/s]
17%|█▋ | 4/24 [00:01<00:04, 4.26it/s]
Total progress: 21%|██ | 5/24 [00:00<00:02, 6.78it/s][A
21%|██ | 5/24 [00:01<00:04, 4.50it/s]
Total progress: 25%|██▌ | 6/24 [00:00<00:02, 6.22it/s][A
25%|██▌ | 6/24 [00:01<00:03, 4.66it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:02, 5.82it/s][A
29%|██▉ | 7/24 [00:01<00:03, 4.77it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:02, 5.58it/s][A
33%|███▎ | 8/24 [00:01<00:03, 4.84it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.39it/s][A
38%|███▊ | 9/24 [00:02<00:03, 4.89it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.28it/s][A
42%|████▏ | 10/24 [00:02<00:02, 4.92it/s]
Total progress: 46%|████▌ | 11/24 [00:01<00:02, 5.19it/s][A
46%|████▌ | 11/24 [00:02<00:02, 4.95it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 5.13it/s][A
50%|█████ | 12/24 [00:02<00:02, 4.96it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 5.10it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.97it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:01, 5.06it/s][A
58%|█████▊ | 14/24 [00:03<00:02, 4.98it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 5.04it/s][A
62%|██████▎ | 15/24 [00:03<00:01, 4.98it/s]
Total progress: 67%|██████▋ | 16/24 [00:02<00:01, 5.03it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.99it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 5.02it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.99it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 5.02it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.99it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:00, 5.01it/s][A
79%|███████▉ | 19/24 [00:04<00:01, 5.00it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 5.01it/s][A
83%|████████▎ | 20/24 [00:04<00:00, 5.00it/s]
Total progress: 88%|████████▊ | 21/24 [00:03<00:00, 5.00it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 5.01it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 5.01it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.99it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 5.00it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.99it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.99it/s][A
100%|██████████| 24/24 [00:05<00:00, 4.99it/s]
100%|██████████| 24/24 [00:05<00:00, 4.74it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 13007.13 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 13007.13 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 11823.58 MB, All loaded to GPU.
Moving model(s) has taken 0.06 seconds
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.99it/s][A
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.84it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 12837.71 MB ... Unload model JointTextEncoder Current free memory is 14598.06 MB ... Unload model KModel Current free memory is 19595.40 MB ... Unload model IntegratedAutoencoderKL Done.
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3302.87 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 19758.48 MB, Model Require: 1752.98 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 16981.50 MB, All loaded to GPU.
Moving model(s) has taken 0.59 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 17999.01 MB ... Done.
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 17998.25 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 17998.25 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 12077.21 MB, All loaded to GPU.
Moving model(s) has taken 1.67 seconds
0%| | 0/24 [00:00<?, ?it/s]
Total progress: 0%| | 0/24 [00:00<?, ?it/s][A
Total progress: 8%|▊ | 2/24 [00:00<00:02, 9.97it/s][A
8%|▊ | 2/24 [00:00<00:04, 5.13it/s]
Total progress: 12%|█▎ | 3/24 [00:00<00:02, 7.09it/s][A
12%|█▎ | 3/24 [00:00<00:04, 5.07it/s]
Total progress: 17%|█▋ | 4/24 [00:00<00:03, 6.13it/s][A
17%|█▋ | 4/24 [00:00<00:03, 5.03it/s]
Total progress: 21%|██ | 5/24 [00:00<00:03, 5.67it/s][A
21%|██ | 5/24 [00:00<00:03, 5.02it/s]
Total progress: 25%|██▌ | 6/24 [00:01<00:03, 5.42it/s][A
25%|██▌ | 6/24 [00:01<00:03, 5.01it/s]
Total progress: 29%|██▉ | 7/24 [00:01<00:03, 5.28it/s][A
29%|██▉ | 7/24 [00:01<00:03, 5.01it/s]
Total progress: 33%|███▎ | 8/24 [00:01<00:03, 5.20it/s][A
33%|███▎ | 8/24 [00:01<00:03, 5.01it/s]
Total progress: 38%|███▊ | 9/24 [00:01<00:02, 5.14it/s][A
38%|███▊ | 9/24 [00:01<00:02, 5.01it/s]
Total progress: 42%|████▏ | 10/24 [00:01<00:02, 5.10it/s][A
42%|████▏ | 10/24 [00:01<00:02, 5.01it/s]
Total progress: 46%|████▌ | 11/24 [00:01<00:02, 5.07it/s][A
46%|████▌ | 11/24 [00:02<00:02, 5.01it/s]
Total progress: 50%|█████ | 12/24 [00:02<00:02, 5.05it/s][A
50%|█████ | 12/24 [00:02<00:02, 5.01it/s]
Total progress: 54%|█████▍ | 13/24 [00:02<00:02, 5.04it/s][A
54%|█████▍ | 13/24 [00:02<00:02, 4.99it/s]
Total progress: 58%|█████▊ | 14/24 [00:02<00:01, 5.01it/s][A
58%|█████▊ | 14/24 [00:02<00:02, 4.99it/s]
Total progress: 62%|██████▎ | 15/24 [00:02<00:01, 5.01it/s][A
62%|██████▎ | 15/24 [00:02<00:01, 4.99it/s]
Total progress: 67%|██████▋ | 16/24 [00:03<00:01, 5.00it/s][A
67%|██████▋ | 16/24 [00:03<00:01, 4.99it/s]
Total progress: 71%|███████ | 17/24 [00:03<00:01, 4.99it/s][A
71%|███████ | 17/24 [00:03<00:01, 4.99it/s]
Total progress: 75%|███████▌ | 18/24 [00:03<00:01, 5.00it/s][A
75%|███████▌ | 18/24 [00:03<00:01, 4.99it/s]
Total progress: 79%|███████▉ | 19/24 [00:03<00:01, 5.00it/s][A
79%|███████▉ | 19/24 [00:03<00:01, 5.00it/s]
Total progress: 83%|████████▎ | 20/24 [00:03<00:00, 5.00it/s][A
83%|████████▎ | 20/24 [00:03<00:00, 4.99it/s]
Total progress: 88%|████████▊ | 21/24 [00:04<00:00, 4.99it/s][A
88%|████████▊ | 21/24 [00:04<00:00, 4.99it/s]
Total progress: 92%|█████████▏| 22/24 [00:04<00:00, 4.99it/s][A
92%|█████████▏| 22/24 [00:04<00:00, 4.98it/s]
Total progress: 96%|█████████▌| 23/24 [00:04<00:00, 4.97it/s][A
96%|█████████▌| 23/24 [00:04<00:00, 4.97it/s]
Total progress: 100%|██████████| 24/24 [00:04<00:00, 4.97it/s][A
100%|██████████| 24/24 [00:04<00:00, 4.97it/s]
100%|██████████| 24/24 [00:04<00:00, 5.00it/s]
[Unload] Trying to free 2657.67 MB for cuda:0 with 0 models keep loaded ... Current free memory is 12997.59 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 12997.59 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 11814.03 MB, All loaded to GPU.
Moving model(s) has taken 0.06 seconds
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.97it/s][A
Total progress: 100%|██████████| 24/24 [00:05<00:00, 4.78it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 12836.16 MB ... Unload model JointTextEncoder Current free memory is 14595.01 MB ... Unload model KModel Current free memory is 19595.40 MB ... Unload model IntegratedAutoencoderKL Done.
################################################################
[1m[32mInstall script for stable-diffusion + Web UI
[1m[34mTested on Debian 11 (Bullseye), Fedora 34+ and openSUSE Leap 15.4 or newer.[0m
################################################################
################################################################
Running on [1m[32mroot[0m user
################################################################
################################################################
Repo already cloned, using it as install directory
################################################################
################################################################
Create and activate python venv
################################################################
################################################################
Launching launch.py...
################################################################
glibc version is 2.39
Check TCMalloc: libtcmalloc_minimal.so.4
libtcmalloc_minimal.so.4 is linked with libc.so,execute LD_PRELOAD=/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4
=============================================================================================
INCOMPATIBLE PYTHON VERSION
This program is tested with 3.10.6 Python, but you have 3.12.3.
If you encounter an error with "RuntimeError: Couldn't install torch." message,
or any other error regarding unsuccessful package (library) installation,
please downgrade (or upgrade) to the latest version of 3.10 Python
and delete current Python and "venv" folder in WebUI's directory.
You can download 3.10 Python from here: https://www.python.org/downloads/release/python-3106/
Use --skip-python-version-check to suppress this warning.
=============================================================================================
Python 3.12.3 (main, Jun 19 2026, 12:46:00) [GCC 13.3.0]
Version: f2.0.1v1.10.1-previous-669-gdfdcbab6
Commit hash: dfdcbab685e57677014f05a3309b48cc87383167
Legacy Preprocessor init warning: Unable to install insightface automatically. Please try run `pip install insightface` manually.
Launching Web UI with arguments: -f --listen --api --enable-insecure-extension-access --xformers --no-half-vae --port 7887
Total VRAM 20017 MB, total RAM 64105 MB
pytorch version: 2.3.1+cu121
WARNING:xformers:A matching Triton is not available, some optimizations will not be enabled
Traceback (most recent call last):
File "/opt/sd-webui/venv/lib/python3.12/site-packages/xformers/__init__.py", line 57, in _is_triton_available
import triton # noqa
^^^^^^^^^^^^^
ModuleNotFoundError: No module named 'triton'
xformers version: 0.0.27
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA RTX 4000 SFF Ada Generation : native
Hint: your device supports --cuda-malloc for potential speed improvements.
VAE dtype preferences: [torch.bfloat16, torch.float32] -> torch.bfloat16
CUDA Using Stream: False
Using xformers cross attention
Using xformers attention for VAE
ControlNet preprocessor location: /opt/sd-webui/models/ControlNetPreprocessor
*** Error loading script: soft_inpainting.py
Traceback (most recent call last):
File "/opt/sd-webui/modules/scripts.py", line 525, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/sd-webui/modules/script_loading.py", line 13, in load_module
module_spec.loader.exec_module(module)
File "<frozen importlib._bootstrap_external>", line 995, in exec_module
File "<frozen importlib._bootstrap>", line 488, in _call_with_frames_removed
File "/opt/sd-webui/extensions-builtin/soft-inpainting/scripts/soft_inpainting.py", line 10, in <module>
from joblib import Parallel, delayed, cpu_count
ModuleNotFoundError: No module named 'joblib'
---
2026-07-11 18:28:21,531 - ControlNet - [0;32mINFO[0m - ControlNet UI callback registered.
Model selected: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
Using online LoRAs in FP16: False
Running on local URL: http://0.0.0.0:7887
To create a public link, set `share=True` in `launch()`.
Startup time: 12.2s (prepare environment: 3.3s, launcher: 0.3s, import torch: 5.3s, other imports: 0.2s, load scripts: 0.8s, create ui: 1.1s, gradio launch: 0.5s, add APIs: 0.7s).
Loading Model: {'checkpoint_info': {'filename': '/opt/sd-webui/models/Stable-diffusion/homofidelisXL_v30SDXL.safetensors', 'hash': '06f31786'}, 'additional_modules': [], 'unet_storage_dtype': None}
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Done.
StateDict Keys: {'unet': 1680, 'vae': 248, 'text_encoder': 197, 'text_encoder_2': 518, 'ignore': 0}
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
K-Model Created: {'storage_dtype': torch.float16, 'computation_dtype': torch.float16}
Model loaded in 0.9s (unload existing model: 0.1s, forge model load: 0.8s).
WARNING:root:Sampler Scheduler autocorrection: "DPM++ 2M" -> "DPM++ 2M", "None" -> "Automatic"
[Unload] Trying to free 3051.58 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 19829.27 MB, Model Require: 1559.68 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 17245.59 MB, All loaded to GPU.
Moving model(s) has taken 0.92 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 18025.57 MB ... Done.
[Unload] Trying to free 7390.16 MB for cuda:0 with 0 models keep loaded ... Current free memory is 18024.89 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 18024.89 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 12103.85 MB, All loaded to GPU.
Moving model(s) has taken 2.91 seconds
0%| | 0/8 [00:00<?, ?it/s]
Total progress: 0%| | 0/8 [00:00<?, ?it/s][A
12%|█▎ | 1/8 [00:00<00:02, 2.99it/s]
Total progress: 38%|███▊ | 3/8 [00:00<00:00, 21.15it/s][A
38%|███▊ | 3/8 [00:00<00:00, 6.36it/s]
62%|██████▎ | 5/8 [00:00<00:00, 7.87it/s]
Total progress: 75%|███████▌ | 6/8 [00:00<00:00, 12.91it/s][A
88%|████████▊ | 7/8 [00:00<00:00, 8.69it/s]
Total progress: 100%|██████████| 8/8 [00:00<00:00, 11.77it/s][A
100%|██████████| 8/8 [00:01<00:00, 7.86it/s]
[Unload] Trying to free 1296.42 MB for cuda:0 with 0 models keep loaded ... Current free memory is 13009.43 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 13009.43 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 11825.87 MB, All loaded to GPU.
Moving model(s) has taken 0.06 seconds
Total progress: 100%|██████████| 8/8 [00:00<00:00, 11.77it/s][A
Total progress: 100%|██████████| 8/8 [00:00<00:00, 8.77it/s]
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Current free memory is 12838.42 MB ... Unload model JointTextEncoder Current free memory is 14598.78 MB ... Unload model KModel Current free memory is 19596.12 MB ... Unload model IntegratedAutoencoderKL Done.