Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Loading SDXL 1.0 fails with RuntimeError: Model config for ViT-bigG-14 not found. #615

Closed
2 tasks done
jsjolund opened this issue Nov 20, 2023 · 2 comments · Fixed by #617
Closed
2 tasks done

Loading SDXL 1.0 fails with RuntimeError: Model config for ViT-bigG-14 not found. #615

jsjolund opened this issue Nov 20, 2023 · 2 comments · Fixed by #617
Labels
bug Something isn't working

Comments

@jsjolund
Copy link
Contributor

jsjolund commented Nov 20, 2023 •
edited
Loading

Has this issue been opened before?

  • It is not in the FAQ, I checked.
  • It is not in the issues, I searched.

Describe the bug

The commit 3e67f55 breaks loading of SD XL - v1.0 VAE fix from civitai and SD XL 1.0 base from huggingface.

$ docker compose --profile auto up --build
[+] Building 0.6s (24/24) FINISHED                                                                                                                            docker:default
 => [auto internal] load .dockerignore                                                                                                                                  0.0s
 => => transferring context: 2B                                                                                                                                         0.0s
 => [auto internal] load build definition from Dockerfile                                                                                                               0.0s
 => => transferring dockerfile: 2.70kB                                                                                                                                  0.0s
 => [auto internal] load metadata for docker.io/pytorch/pytorch:2.1.0-cuda12.1-cudnn8-runtime                                                                           0.5s
 => [auto internal] load metadata for docker.io/alpine/git:2.36.2                                                                                                       0.0s
 => [auto internal] load build context                                                                                                                                  0.0s
 => => transferring context: 122B                                                                                                                                       0.0s
 => [auto stage-1  1/11] FROM docker.io/pytorch/pytorch:2.1.0-cuda12.1-cudnn8-runtime@sha256:e4aaefef0c96318759160ff971b527ae61ee306a1204c5f6e907c4b45f05b8a3           0.0s
 => [auto download 1/8] FROM docker.io/alpine/git:2.36.2                                                                                                                0.0s
 => CACHED [auto stage-1  2/11] RUN --mount=type=cache,target=/var/cache/apt   apt-get update &&   apt-get install -y fonts-dejavu-core rsync git jq moreutils aria2    0.0s
 => CACHED [auto stage-1  3/11] RUN --mount=type=cache,target=/root/.cache/pip   git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui.git &&   cd stable-  0.0s
 => CACHED [auto download 2/8] COPY clone.sh /clone.sh                                                                                                                  0.0s
 => CACHED [auto download 3/8] RUN . /clone.sh stable-diffusion-stability-ai https://github.com/Stability-AI/stablediffusion.git cf1d67a6fd5ea1aa600c4df58e5b47da45f6b  0.0s
 => CACHED [auto download 4/8] RUN . /clone.sh CodeFormer https://github.com/sczhou/CodeFormer.git c5b4593074ba6214284d6acd5f1719b6c5d739af   && rm -rf assets inputs   0.0s
 => CACHED [auto download 5/8] RUN . /clone.sh BLIP https://github.com/salesforce/BLIP.git 48211a1594f1321b00f14c9f7a5b4813144b2fb9                                     0.0s
 => CACHED [auto download 6/8] RUN . /clone.sh k-diffusion https://github.com/crowsonkb/k-diffusion.git ab527a9a6d347f364e3d185ba6d714e22d80cb3c                        0.0s
 => CACHED [auto download 7/8] RUN . /clone.sh clip-interrogator https://github.com/pharmapsychotic/clip-interrogator 2cf03aaf6e704197fd0dae7c7f96aa59cf1b11c9          0.0s
 => CACHED [auto download 8/8] RUN . /clone.sh generative-models https://github.com/Stability-AI/generative-models 45c443b316737a4ab6e40413d7794a7f5657c19f             0.0s
 => CACHED [auto stage-1  4/11] COPY --from=download /repositories/ /stable-diffusion-webui/repositories/                                                               0.0s
 => CACHED [auto stage-1  5/11] RUN mkdir /stable-diffusion-webui/interrogate && cp /stable-diffusion-webui/repositories/clip-interrogator/clip_interrogator/data/* /s  0.0s
 => CACHED [auto stage-1  6/11] RUN --mount=type=cache,target=/root/.cache/pip   pip install -r /stable-diffusion-webui/repositories/CodeFormer/requirements.txt        0.0s
 => CACHED [auto stage-1  7/11] RUN --mount=type=cache,target=/root/.cache/pip   pip install pyngrok xformers   git+https://github.com/TencentARC/GFPGAN.git@8d2447a2d  0.0s
 => CACHED [auto stage-1  8/11] COPY . /docker                                                                                                                          0.0s
 => CACHED [auto stage-1  9/11] RUN   sed -i 's/in_app_dir = .*/in_app_dir = True/g' /opt/conda/lib/python3.10/site-packages/gradio/routes.py &&   git config --global  0.0s
 => CACHED [auto stage-1 10/11] WORKDIR /stable-diffusion-webui                                                                                                         0.0s
 => [auto] exporting to image                                                                                                                                           0.0s
 => => exporting layers                                                                                                                                                 0.0s
 => => writing image sha256:36ba8fb9c0bd9085554c0f9cf076ed7b266f24f0f28494af43000a36bb5a944e                                                                            0.0s
 => => naming to docker.io/library/sd-auto:68                                                                                                                           0.0s
[+] Running 1/0
 ✔ Container webui-docker-auto-1  Created                                                                                                                               0.0s 
Attaching to auto-1
auto-1  | /stable-diffusion-webui
auto-1  | total 704K
auto-1  | drwxr-xr-x 1 root root 4.0K Nov 20 22:19 .
auto-1  | drwxr-xr-x 1 root root 4.0K Nov 20 21:53 ..
auto-1  | -rw-r--r-- 1 root root   48 Nov 20 21:08 .eslintignore
auto-1  | -rw-r--r-- 1 root root 3.4K Nov 20 21:08 .eslintrc.js
auto-1  | drwxr-xr-x 8 root root 4.0K Nov 20 21:08 .git
auto-1  | -rw-r--r-- 1 root root   55 Nov 20 21:08 .git-blame-ignore-revs
auto-1  | drwxr-xr-x 4 root root 4.0K Nov 20 21:08 .github
auto-1  | -rw-r--r-- 1 root root  495 Nov 20 21:08 .gitignore
auto-1  | -rw-r--r-- 1 root root  119 Nov 20 21:08 .pylintrc
auto-1  | -rw-r--r-- 1 root root  33K Nov 20 21:08 CHANGELOG.md
auto-1  | -rw-r--r-- 1 root root  243 Nov 20 21:08 CITATION.cff
auto-1  | -rw-r--r-- 1 root root  657 Nov 20 21:08 CODEOWNERS
auto-1  | -rw-r--r-- 1 root root  35K Nov 20 21:08 LICENSE.txt
auto-1  | -rw-r--r-- 1 root root  12K Nov 20 21:08 README.md
auto-1  | drwxr-xr-x 2 root root 4.0K Nov 20 21:53 __pycache__
auto-1  | -rw-r--r-- 1 root root 5.5K Nov 20 22:19 cache.json
auto-1  | lrwxrwxrwx 1 root root   29 Nov 20 22:19 config.json -> /data/config/auto/config.json
auto-1  | lrwxrwxrwx 1 root root   31 Nov 20 22:19 config_states -> /data/config/auto/config_states
auto-1  | drwxr-xr-x 2 root root 4.0K Nov 20 21:08 configs
auto-1  | lrwxrwxrwx 1 root root   16 Nov 20 22:19 embeddings -> /data/embeddings
auto-1  | -rw-r--r-- 1 root root  167 Nov 20 21:08 environment-wsl2.yaml
auto-1  | lrwxrwxrwx 1 root root   28 Nov 20 22:19 extensions -> /data/config/auto/extensions
auto-1  | drwxr-xr-x 1 root root 4.0K Nov 20 21:08 extensions-builtin
auto-1  | drwxr-xr-x 2 root root 4.0K Nov 20 21:08 html
auto-1  | drwxr-xr-x 2 root root 4.0K Nov 20 21:09 interrogate
auto-1  | drwxr-xr-x 2 root root 4.0K Nov 20 21:08 javascript
auto-1  | -rw-r--r-- 1 root root 1.3K Nov 20 21:08 launch.py
auto-1  | drwxr-xr-x 2 root root 4.0K Nov 20 21:08 localizations
auto-1  | lrwxrwxrwx 1 root root   12 Nov 20 22:19 models -> /data/models
auto-1  | drwxr-xr-x 1 root root 4.0K Nov 20 21:53 modules
auto-1  | -rw-r--r-- 1 root root  185 Nov 20 21:08 package.json
auto-1  | -rw-r--r-- 1 root root  763 Nov 20 21:08 pyproject.toml
auto-1  | drwxr-xr-x 1 root root 4.0K Oct 30 20:01 repositories
auto-1  | -rw-r--r-- 1 root root   49 Nov 20 21:08 requirements-test.txt
auto-1  | -rw-r--r-- 1 root root  360 Nov 20 21:08 requirements.txt
auto-1  | -rw-r--r-- 1 root root  556 Nov 20 21:08 requirements_versions.txt
auto-1  | -rw-r--r-- 1 root root 411K Nov 20 21:08 screenshot.png
auto-1  | -rw-r--r-- 1 root root 4.7K Nov 20 21:08 script.js
auto-1  | drwxr-xr-x 1 root root 4.0K Nov 20 21:53 scripts
auto-1  | -rw-r--r-- 1 root root  21K Nov 20 21:08 style.css
auto-1  | lrwxrwxrwx 1 root root   28 Nov 20 22:19 styles.csv -> /data/config/auto/styles.csv
auto-1  | drwxr-xr-x 3 root root 4.0K Nov 20 21:08 test
auto-1  | drwxr-xr-x 2 root root 4.0K Nov 20 21:08 textual_inversion_templates
auto-1  | lrwxrwxrwx 1 root root   32 Nov 20 22:19 ui-config.json -> /data/config/auto/ui-config.json
auto-1  | -rw-r--r-- 1 root root  670 Nov 20 21:08 webui-macos-env.sh
auto-1  | -rw-r--r-- 1 root root   84 Nov 20 21:08 webui-user.bat
auto-1  | -rw-r--r-- 1 root root 1.4K Nov 20 21:08 webui-user.sh
auto-1  | -rw-r--r-- 1 root root 2.2K Nov 20 21:08 webui.bat
auto-1  | -rw-r--r-- 1 root root 5.4K Nov 20 21:08 webui.py
auto-1  | -rwxr-xr-x 1 root root 8.0K Nov 20 21:08 webui.sh
auto-1  | Mounted embeddings
auto-1  | Mounted .cache
auto-1  | Mounted styles.csv
auto-1  | Mounted ui-config.json
auto-1  | Mounted models
auto-1  | Mounted .cache
auto-1  | Mounted config_states
auto-1  | Mounted config.json
auto-1  | Mounted extensions
auto-1  | Installing extension dependencies (if any)
auto-1  | Checkpoint sd_xl_base_1.0.safetensors [31e35c80fc] not found; loading fallback sd-v1-5-inpainting.ckpt [c6bbc15e32]
auto-1  | Loading weights [c6bbc15e32] from /stable-diffusion-webui/models/Stable-diffusion/sd-v1-5-inpainting.ckpt
auto-1  | Running on local URL:  http://0.0.0.0:7860
auto-1  | 
auto-1  | To create a public link, set `share=True` in `launch()`.
auto-1  | Startup time: 6.5s (import torch: 2.6s, import gradio: 0.9s, setup paths: 1.3s, initialize shared: 0.1s, other imports: 0.5s, load scripts: 0.3s, create ui: 0.3s, gradio launch: 0.2s).
auto-1  | Creating model from config: /stable-diffusion-webui/configs/v1-inpainting-inference.yaml
auto-1  | Loading VAE weights specified in settings: /stable-diffusion-webui/models/VAE/sdxl_vae.safetensors
auto-1  | Applying attention optimization: xformers... done.
auto-1  | Model loaded in 5.0s (load weights from disk: 2.6s, create model: 0.3s, apply weights to model: 1.1s, apply half(): 0.4s, calculate empty prompt: 0.4s).
auto-1  | Reusing loaded model sd-v1-5-inpainting.ckpt [c6bbc15e32] to load sdXL_v10VAEFix.safetensors
auto-1  | Calculating sha256 for /stable-diffusion-webui/models/Stable-diffusion/sdXL_v10VAEFix.safetensors: e6bb9ea85bbf7bf6478a7c6d18b71246f22e95d41bcdd80ed40aa212c33cfeff
auto-1  | Loading weights [e6bb9ea85b] from /stable-diffusion-webui/models/Stable-diffusion/sdXL_v10VAEFix.safetensors
auto-1  | Creating model from config: /stable-diffusion-webui/repositories/generative-models/configs/inference/sd_xl_base.yaml
auto-1  | ERROR:root:Model config for ViT-bigG-14 not found; available models ['mt5-base-ViT-B-32', 'mt5-xl-ViT-H-14', 'RN50', 'RN50-quickgelu', 'RN50x4', 'RN50x16', 'RN50x64', 'RN101', 'RN101-quickgelu', 'roberta-ViT-B-32', 'timm-convnext_base', 'timm-convnext_large', 'timm-convnext_xlarge', 'timm-efficientnetv2_rw_s', 'timm-resnetaa50d', 'timm-swin_base_patch4_window7_224', 'timm-vit_medium_patch16_gap_256', 'timm-vit_relpos_medium_patch16_cls_224', 'ViT-B-16', 'ViT-B-16-plus', 'ViT-B-16-plus-240', 'ViT-B-32', 'ViT-B-32-plus-256', 'ViT-B-32-quickgelu', 'ViT-e-14', 'ViT-g-14', 'ViT-G-14', 'ViT-H-14', 'ViT-H-16', 'ViT-L-14', 'ViT-L-14-280', 'ViT-L-14-336', 'ViT-L-16', 'ViT-L-16-320', 'ViT-M-16', 'ViT-M-16-alt', 'ViT-M-32', 'ViT-M-32-alt', 'ViT-S-16', 'ViT-S-16-alt', 'ViT-S-32', 'ViT-S-32-alt', 'xlm-roberta-base-ViT-B-32', 'xlm-roberta-large-ViT-H-14'].
auto-1  | creating model quickly: RuntimeError
auto-1  | Traceback (most recent call last):
auto-1  |   File "/opt/conda/lib/python3.10/threading.py", line 973, in _bootstrap
auto-1  |     self._bootstrap_inner()
auto-1  |   File "/opt/conda/lib/python3.10/threading.py", line 1016, in _bootstrap_inner
auto-1  |     self.run()
auto-1  |   File "/opt/conda/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 807, in run
auto-1  |     result = context.run(func, *args)
auto-1  |   File "/opt/conda/lib/python3.10/site-packages/gradio/utils.py", line 707, in wrapper
auto-1  |     response = f(*args, **kwargs)
auto-1  |   File "/stable-diffusion-webui/modules/ui_settings.py", line 272, in <lambda>
auto-1  |     fn=lambda value, k=k: self.run_settings_single(value, key=k),
auto-1  |   File "/stable-diffusion-webui/modules/ui_settings.py", line 90, in run_settings_single
auto-1  |     if value is None or not opts.set(key, value):
auto-1  |   File "/stable-diffusion-webui/modules/options.py", line 140, in set
auto-1  |     option.onchange()
auto-1  |   File "/stable-diffusion-webui/modules/call_queue.py", line 13, in f
auto-1  |     res = func(*args, **kwargs)
auto-1  |   File "/stable-diffusion-webui/modules/initialize_util.py", line 170, in <lambda>
auto-1  |     shared.opts.onchange("sd_model_checkpoint", wrap_queued_call(lambda: sd_models.reload_model_weights()), call=False)
auto-1  |   File "/stable-diffusion-webui/modules/sd_models.py", line 751, in reload_model_weights
auto-1  |     load_model(checkpoint_info, already_loaded_state_dict=state_dict)
auto-1  |   File "/stable-diffusion-webui/modules/sd_models.py", line 602, in load_model
auto-1  |     sd_model = instantiate_from_config(sd_config.model)
auto-1  |   File "/stable-diffusion-webui/repositories/stable-diffusion-stability-ai/ldm/util.py", line 89, in instantiate_from_config
auto-1  |     return get_obj_from_str(config["target"])(**config.get("params", dict()))
auto-1  |   File "/stable-diffusion-webui/repositories/generative-models/sgm/models/diffusion.py", line 61, in __init__
auto-1  |     self.conditioner = instantiate_from_config(
auto-1  |   File "/stable-diffusion-webui/repositories/generative-models/sgm/util.py", line 175, in instantiate_from_config
auto-1  |     return get_obj_from_str(config["target"])(**config.get("params", dict()))
auto-1  |   File "/stable-diffusion-webui/repositories/generative-models/sgm/modules/encoders/modules.py", line 88, in __init__
auto-1  |     embedder = instantiate_from_config(embconfig)
auto-1  |   File "/stable-diffusion-webui/repositories/generative-models/sgm/util.py", line 175, in instantiate_from_config
auto-1  |     return get_obj_from_str(config["target"])(**config.get("params", dict()))
auto-1  |   File "/stable-diffusion-webui/repositories/generative-models/sgm/modules/encoders/modules.py", line 428, in __init__
auto-1  |     model, _, _ = open_clip.create_model_and_transforms(
auto-1  |   File "/stable-diffusion-webui/modules/sd_disable_initialization.py", line 65, in create_model_and_transforms_without_pretrained
auto-1  |     return self.create_model_and_transforms(*args, pretrained=None, **kwargs)
auto-1  |   File "/opt/conda/lib/python3.10/site-packages/open_clip/factory.py", line 201, in create_model_and_transforms
auto-1  |     model = create_model(
auto-1  |   File "/opt/conda/lib/python3.10/site-packages/open_clip/factory.py", line 131, in create_model
auto-1  |     raise RuntimeError(f'Model config for {model_name} not found.')
auto-1  | RuntimeError: Model config for ViT-bigG-14 not found.
auto-1  | 
auto-1  | Failed to create model quickly; will retry using slow method.
auto-1  | ERROR:root:Model config for ViT-bigG-14 not found; available models ['mt5-base-ViT-B-32', 'mt5-xl-ViT-H-14', 'RN50', 'RN50-quickgelu', 'RN50x4', 'RN50x16', 'RN50x64', 'RN101', 'RN101-quickgelu', 'roberta-ViT-B-32', 'timm-convnext_base', 'timm-convnext_large', 'timm-convnext_xlarge', 'timm-efficientnetv2_rw_s', 'timm-resnetaa50d', 'timm-swin_base_patch4_window7_224', 'timm-vit_medium_patch16_gap_256', 'timm-vit_relpos_medium_patch16_cls_224', 'ViT-B-16', 'ViT-B-16-plus', 'ViT-B-16-plus-240', 'ViT-B-32', 'ViT-B-32-plus-256', 'ViT-B-32-quickgelu', 'ViT-e-14', 'ViT-g-14', 'ViT-G-14', 'ViT-H-14', 'ViT-H-16', 'ViT-L-14', 'ViT-L-14-280', 'ViT-L-14-336', 'ViT-L-16', 'ViT-L-16-320', 'ViT-M-16', 'ViT-M-16-alt', 'ViT-M-32', 'ViT-M-32-alt', 'ViT-S-16', 'ViT-S-16-alt', 'ViT-S-32', 'ViT-S-32-alt', 'xlm-roberta-base-ViT-B-32', 'xlm-roberta-large-ViT-H-14'].
auto-1  | changing setting sd_model_checkpoint to sdXL_v10VAEFix.safetensors: RuntimeError
auto-1  | Traceback (most recent call last):
auto-1  |   File "/stable-diffusion-webui/modules/options.py", line 140, in set
auto-1  |     option.onchange()
auto-1  |   File "/stable-diffusion-webui/modules/call_queue.py", line 13, in f
auto-1  |     res = func(*args, **kwargs)
auto-1  |   File "/stable-diffusion-webui/modules/initialize_util.py", line 170, in <lambda>
auto-1  |     shared.opts.onchange("sd_model_checkpoint", wrap_queued_call(lambda: sd_models.reload_model_weights()), call=False)
auto-1  |   File "/stable-diffusion-webui/modules/sd_models.py", line 751, in reload_model_weights
auto-1  |     load_model(checkpoint_info, already_loaded_state_dict=state_dict)
auto-1  |   File "/stable-diffusion-webui/modules/sd_models.py", line 611, in load_model
auto-1  |     sd_model = instantiate_from_config(sd_config.model)
auto-1  |   File "/stable-diffusion-webui/repositories/stable-diffusion-stability-ai/ldm/util.py", line 89, in instantiate_from_config
auto-1  |     return get_obj_from_str(config["target"])(**config.get("params", dict()))
auto-1  |   File "/stable-diffusion-webui/repositories/generative-models/sgm/models/diffusion.py", line 61, in __init__
auto-1  |     self.conditioner = instantiate_from_config(
auto-1  |   File "/stable-diffusion-webui/repositories/generative-models/sgm/util.py", line 175, in instantiate_from_config
auto-1  |     return get_obj_from_str(config["target"])(**config.get("params", dict()))
auto-1  |   File "/stable-diffusion-webui/repositories/generative-models/sgm/modules/encoders/modules.py", line 88, in __init__
auto-1  |     embedder = instantiate_from_config(embconfig)
auto-1  |   File "/stable-diffusion-webui/repositories/generative-models/sgm/util.py", line 175, in instantiate_from_config
auto-1  |     return get_obj_from_str(config["target"])(**config.get("params", dict()))
auto-1  |   File "/stable-diffusion-webui/repositories/generative-models/sgm/modules/encoders/modules.py", line 428, in __init__
auto-1  |     model, _, _ = open_clip.create_model_and_transforms(
auto-1  |   File "/opt/conda/lib/python3.10/site-packages/open_clip/factory.py", line 201, in create_model_and_transforms
auto-1  |     model = create_model(
auto-1  |   File "/opt/conda/lib/python3.10/site-packages/open_clip/factory.py", line 131, in create_model
auto-1  |     raise RuntimeError(f'Model config for {model_name} not found.')
auto-1  | RuntimeError: Model config for ViT-bigG-14 not found.
auto-1  |

Which UI

auto

Hardware / Software

  • OS: Arch Linux
  • Docker Version: 24.0.7
  • Docker compose version: 2.23.1
  • Repo version: 3e67f55
  • RAM: 32 Gb
  • GPU/VRAM: Nvidia RTX 4090 / 24 Gb

Steps to Reproduce

git clone https://github.com/AbdBarho/stable-diffusion-webui-docker.git
cd stable-diffusion-webui-docker
docker compose --profile download up --build
docker compose --profile auto up --build
  1. SD 1.5 loads fine and is usable at http://localhost:7860. Ctrl+C to stop docker compose.
  2. Download the SD XL 1.0 base and refiner from civitai or huggingface.
mv sdXL_v10RefinerVAEFix.safetensors sdXL_v10VAEFix.safetensors data/models/Stable-diffusion/`
docker compose --profile auto up --build
  1. Loading SD XL 1.0 fails in the webui with RuntimeError: Model config for ViT-bigG-14 not found.

Additional context

Related issues:

It seems the solution is pip install open-clip-torch==2.20.0, however, when I added this to the auto Dockerfile, it fails with:

12.36 Collecting xformers
12.36   Obtaining dependency information for xformers from https://files.pythonhosted.org/packages/bb/9c/bb1a40d5e8db2b34dd6e6c0f851e86b38a3d0840fff1bf14240eff7d3da6/xformers-0.0.22.post7-cp310-cp310-manylinux2014_x86_64.whl.metadata
12.37   Using cached xformers-0.0.22.post7-cp310-cp310-manylinux2014_x86_64.whl.metadata (1.0 kB)
12.37 ERROR: Cannot install open-clip-torch 2.7.0 (from git+https://github.com/mlfoundations/open_clip.git@bb6e834e9c70d9c27d0dc3ecedeebeaeb1ffad6b) and open-clip-torch==2.20.0 because these package versions have conflicting dependencies.
12.37 
12.37 The conflict is caused by:
12.37     The user requested open-clip-torch==2.20.0
12.37     The user requested open-clip-torch 2.7.0 (from git+https://github.com/mlfoundations/open_clip.git@bb6e834e9c70d9c27d0dc3ecedeebeaeb1ffad6b)
12.37 
12.37 To fix this you could try to:
12.37 1. loosen the range of package versions you've specified
12.37 2. remove package versions to allow pip attempt to solve the dependency conflict
12.37 
12.37 ERROR: ResolutionImpossible: for help visit https://pip.pypa.io/en/latest/topics/dependency-resolution/#dealing-with-dependency-conflicts

Reverting to a2561f2 fixes the issue, as long as I add pip install httpx==0.24.1 to the auto Dockerfile, to fix this issue.
@jsjolund jsjolund added the bug Something isn't working label Nov 20, 2023
@jsjolund
Copy link
Contributor Author

jsjolund commented Nov 21, 2023 •
edited
Loading

I was able to fix this by updating the auto Dockerfile open_clip version to the one specified in the auto stable-diffusion-webui requirements.

Replace here:

git+https://github.com/mlfoundations/open_clip.git@bb6e834e9c70d9c27d0dc3ecedeebeaeb1ffad6b

with

git+https://github.com/mlfoundations/[email protected]

Start the deployment again with:

docker compose --profile auto up --build

Then SDXL 1.0 loads without problems.

jsjolund added a commit to jsjolund/stable-diffusion-webui-docker that referenced this issue Nov 21, 2023
@jsjolund
Fixes AbdBarho#615, update open_clip in services/AUTOMATIC1111/Docker…
631d9a1 
…file
jsjolund added a commit to jsjolund/stable-diffusion-webui-docker that referenced this issue Nov 21, 2023
@jsjolund
Fixes AbdBarho#615, update open_clip to v2.20.0 in services/AUTOMATIC…
93dbd1e 
…1111/Dockerfile
@jsjolund jsjolund mentioned this issue Nov 21, 2023
Merged
sf666 added a commit to sf666/sd that referenced this issue Nov 28, 2023
@sf666
Merge commit '93dbd1ecaf903ad24dd510caa1903e85d5d80050'
8272784 
* commit '93dbd1ecaf903ad24dd510caa1903e85d5d80050':
  Fixes AbdBarho#615, update open_clip to v2.20.0 in services/AUTOMATIC1111/Dockerfile
@adamflorizone adamflorizone mentioned this issue Nov 28, 2023
Closed
1 task
mashb1t added a commit to mashb1t/stable-diffusion-webui-docker that referenced this issue Dec 5, 2023
@mashb1t
Fix open_clip version issue
051c28d 
fixes RuntimeError: Model config for ViT-bigG-14 not found.

use https://github.com/mlfoundations/open_clip/releases/tag/v2.23.0

see AbdBarho#615
@mashb1t mashb1t mentioned this issue Dec 5, 2023
Closed
@fchangjun
Copy link

I encountered the same issue, but my open-clip-torch version has been upgraded to 2.2.0
2d03246d71e135179713d131a7d8ad18

ERROR:root:Model config for ViT-bigG-14 not found; available models ['mt5-base-ViT-B-32', 'mt5-xl-ViT-H-14', 'RN50', 'RN50-quickgelu', 'RN50x4', 'RN50x16', 'RN50x64', 'RN101', 'RN101-quickgelu', 'roberta-ViT-B-32', 'timm-convnext_base', 'timm-convnext_large', 'timm-convnext_xlarge', 'timm-efficientnetv2_rw_s', 'timm-resnetaa50d', 'timm-swin_base_patch4_window7_224', 'timm-vit_medium_patch16_gap_256', 'timm-vit_relpos_medium_patch16_cls_224', 'ViT-B-16', 'ViT-B-16-plus', 'ViT-B-16-plus-240', 'ViT-B-32', 'ViT-B-32-plus-256', 'ViT-B-32-quickgelu', 'ViT-e-14', 'ViT-g-14', 'ViT-H-14', 'ViT-H-16', 'ViT-L-14', 'ViT-L-14-280', 'ViT-L-14-336', 'ViT-L-16', 'ViT-L-16-320', 'ViT-M-16', 'ViT-M-16-alt', 'ViT-M-32', 'ViT-M-32-alt', 'ViT-S-16', 'ViT-S-16-alt', 'ViT-S-32', 'ViT-S-32-alt', 'xlm-roberta-base-ViT-B-32', 'xlm-roberta-large-ViT-H-14'].
changing setting sd_model_checkpoint to SDXL/deepblueXL_v021.safetensors [e597feacad]: RuntimeError
Traceback (most recent call last):
  File "/stable-diffusion-webui/modules/options.py", line 140, in set
    option.onchange()
  File "/stable-diffusion-webui/modules/call_queue.py", line 13, in f
    res = func(*args, **kwargs)
  File "/stable-diffusion-webui/modules/initialize_util.py", line 170, in <lambda>
    shared.opts.onchange("sd_model_checkpoint", wrap_queued_call(lambda: sd_models.reload_model_weights()), call=False)
  File "/stable-diffusion-webui/modules/sd_models.py", line 751, in reload_model_weights
    load_model(checkpoint_info, already_loaded_state_dict=state_dict)
  File "/stable-diffusion-webui/modules/sd_models.py", line 611, in load_model
    sd_model = instantiate_from_config(sd_config.model)
  File "/stable-diffusion-webui/repositories/stable-diffusion-stability-ai/ldm/util.py", line 89, in instantiate_from_config
    return get_obj_from_str(config["target"])(**config.get("params", dict()))
  File "/stable-diffusion-webui/repositories/generative-models/sgm/models/diffusion.py", line 61, in __init__
    self.conditioner = instantiate_from_config(
  File "/stable-diffusion-webui/repositories/generative-models/sgm/util.py", line 175, in instantiate_from_config
    return get_obj_from_str(config["target"])(**config.get("params", dict()))
  File "/stable-diffusion-webui/repositories/generative-models/sgm/modules/encoders/modules.py", line 88, in __init__
    embedder = instantiate_from_config(embconfig)
  File "/stable-diffusion-webui/repositories/generative-models/sgm/util.py", line 175, in instantiate_from_config
    return get_obj_from_str(config["target"])(**config.get("params", dict()))
  File "/stable-diffusion-webui/repositories/generative-models/sgm/modules/encoders/modules.py", line 428, in __init__
    model, _, _ = open_clip.create_model_and_transforms(
  File "/usr/local/lib/python3.10/site-packages/open_clip/factory.py", line 201, in create_model_and_transforms
    model = create_model(
  File "/usr/local/lib/python3.10/site-packages/open_clip/factory.py", line 131, in create_model
    raise RuntimeError(f'Model config for {model_name} not found.')
RuntimeError: Model config for ViT-bigG-14 not found.```

AbdBarho added a commit that referenced this issue Jan 1, 2024
@jsjolund @AbdBarho
Update open_clip to v2.20.0 in Auto (#617)
60c4832 
Fixes #615.

Updates `open-clip-torch` to the one specified in auto's
[requirements_versions.txt](https://github.com/AUTOMATIC1111/stable-diffusion-webui/blob/master/requirements_versions.txt#L18).

---------

Co-authored-by: AbdBarho <[email protected]>
yarmand pushed a commit to yarmand/stable-diffusion-webui-docker that referenced this issue Feb 15, 2024
@jsjolund @AbdBarho @yarmand
Update open_clip to v2.20.0 in Auto (AbdBarho#617)
a672767 
Fixes AbdBarho#615.

Updates `open-clip-torch` to the one specified in auto's
[requirements_versions.txt](https://github.com/AUTOMATIC1111/stable-diffusion-webui/blob/master/requirements_versions.txt#L18).

---------

Co-authored-by: AbdBarho <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
bug Something isn't working
Projects
None yet
Milestone
No milestone
2 participants
@jsjolund @fchangjun