Stable-Diffusion-Webui Docker Container Nvidia

[cgroovertech]

Hello all!

I've come so close to docker composing an A1111 stable-diffusion-webui in one go. I'm having issues running the webui.sh automatically with logs after I compose the image. Please see my logs below.

Looking for any help or input.

#dockerfile
FROM pytorch/pytorch
RUN apt update && apt upgrade -y
RUN apt install git -y
RUN apt install nano -y
RUN git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui
RUN cd /workspace/stable-diffusion-webui
RUN apt update
RUN apt install ffmpeg libsm6 libxext6 -y

#install dependencies
RUN mkdir repositories
RUN git clone https://github.com/CompVis/stable-diffusion.git repositories/stable-diffusion
RUN git clone https://github.com/CompVis/taming-transformers.git repositories/taming-transformers
RUN git clone https://github.com/sczhou/CodeFormer.git repositories/CodeFormer
RUN git clone https://github.com/salesforce/BLIP.git repositories/BLIP

# install requirements of Stable Diffusion
RUN pip install transformers==4.19.2 diffusers invisible-watermark --prefer-binary

# install k-diffusion
RUN pip install git+https://github.com/crowsonkb/k-diffusion.git --prefer-binary

# (optional) install GFPGAN (face restoration)
RUN pip install git+https://github.com/TencentARC/GFPGAN.git --prefer-binary

# (optional) install requirements for CodeFormer (face restoration)
RUN pip install -r repositories/CodeFormer/requirements.txt --prefer-binary

# install requirements of web ui
RUN pip install -r /workspace/stable-diffusion-webui/requirements.txt  --prefer-binary

# update numpy to latest version
RUN pip install -U numpy  --prefer-binary

# install and configure virtualenv
RUN pip install virtualenv 
RUN pip install virtualenvwrapper
RUN python -m venv /workspace/stable-diffusion-webui/venv
RUN rm /bin/sh && ln -s /bin/bash /bin/sh
RUN source /workspace/stable-diffusion-webui/venv/bin/activate
RUN python -m pip install --upgrade pip wheel

EXPOSE 7860
ENTRYPOINT ["python /workspace/stable-diffusion-webui/lauch.py"]


#docker-compose.yml
version: "3.5"
services:
  a1111:
    build: .
    ports:
      - "7860:7860"
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]
    environment:
     - PORT=7861

$ ls
docker-compose.yml  dockerfile
$ docker-compose -f docker-compose.yml up -d
Building a1111
[+] Building 0.0s (29/29) FINISHED                                                                                                                    
 => [internal] load .dockerignore                                                                                                                0.0s
 => => transferring context: 2B                                                                                                                  0.0s
 => [internal] load build definition from dockerfile                                                                                             0.0s
 => => transferring dockerfile: 1.78kB                                                                                                           0.0s
 => [internal] load metadata for docker.io/pytorch/pytorch:latest                                                                                0.0s
 => [ 1/25] FROM docker.io/pytorch/pytorch                                                                                                       0.0s
 => CACHED [ 2/25] RUN apt update && apt upgrade -y                                                                                              0.0s
 => CACHED [ 3/25] RUN apt install git -y                                                                                                        0.0s
 => CACHED [ 4/25] RUN apt install nano -y                                                                                                       0.0s
 => CACHED [ 5/25] RUN git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui                                                         0.0s
 => CACHED [ 6/25] RUN cd /workspace/stable-diffusion-webui                                                                                      0.0s
 => CACHED [ 7/25] RUN apt update                                                                                                                0.0s
 => CACHED [ 8/25] RUN apt install ffmpeg libsm6 libxext6 -y                                                                                     0.0s
 => CACHED [ 9/25] RUN mkdir repositories                                                                                                        0.0s
 => CACHED [10/25] RUN git clone https://github.com/CompVis/stable-diffusion.git repositories/stable-diffusion                                   0.0s
 => CACHED [11/25] RUN git clone https://github.com/CompVis/taming-transformers.git repositories/taming-transformers                             0.0s
 => CACHED [12/25] RUN git clone https://github.com/sczhou/CodeFormer.git repositories/CodeFormer                                                0.0s
 => CACHED [13/25] RUN git clone https://github.com/salesforce/BLIP.git repositories/BLIP                                                        0.0s
 => CACHED [14/25] RUN pip install transformers==4.19.2 diffusers invisible-watermark --prefer-binary                                            0.0s
 => CACHED [15/25] RUN pip install git+https://github.com/crowsonkb/k-diffusion.git --prefer-binary                                              0.0s
 => CACHED [16/25] RUN pip install git+https://github.com/TencentARC/GFPGAN.git --prefer-binary                                                  0.0s
 => CACHED [17/25] RUN pip install -r repositories/CodeFormer/requirements.txt --prefer-binary                                                   0.0s
 => CACHED [18/25] RUN pip install -r /workspace/stable-diffusion-webui/requirements.txt  --prefer-binary                                        0.0s
 => CACHED [19/25] RUN pip install -U numpy  --prefer-binary                                                                                     0.0s
 => CACHED [20/25] RUN pip install virtualenv                                                                                                    0.0s
 => CACHED [21/25] RUN pip install virtualenvwrapper                                                                                             0.0s
 => CACHED [22/25] RUN python -m venv /workspace/stable-diffusion-webui/venv                                                                     0.0s
 => CACHED [23/25] RUN rm /bin/sh && ln -s /bin/bash /bin/sh                                                                                     0.0s
 => CACHED [24/25] RUN source /workspace/stable-diffusion-webui/venv/bin/activate                                                                0.0s
 => CACHED [25/25] RUN python -m pip install --upgrade pip wheel                                                                                 0.0s
 => exporting to image                                                                                                                           0.0s
 => => exporting layers                                                                                                                          0.0s
 => => writing image sha256:99960d4cc930d5bd39f636055f4cc441042929a754606ffab659d3170848a7a0                                                     0.0s
 => => naming to docker.io/library/a1111_a1111                                                                                                   0.0s
WARNING: Image for service a1111 was built because it did not already exist. To rebuild this image you must use `docker-compose build` or `docker-compose up --build`.
Creating a1111_a1111_1 ... error

ERROR: for a1111_a1111_1  Cannot start service a1111: failed to create shim task: OCI runtime create failed: runc create failed: unable to start container process: exec: "python /workspace/stable-diffusion-webui/lauch.py": 
stat python /workspace/stable-diffusion-webui/lauch.py: no such file or directory: unknown

ERROR: for a1111  Cannot start service a1111: failed to create shim task: OCI runtime create failed: runc create failed: unable to start container process: exec: "python /workspace/stable-diffusion-webui/lauch.py": 
stat python /workspace/stable-diffusion-webui/lauch.py: no such file or directory: unknown
ERROR: Encountered errors while bringing up the project.

[Bob-AFei]

Hi there, you can simply use my Docker image:
https://hub.docker.com/repository/docker/bobzhao1210/diffusion-webui/general

[cgroovertech]

Thank you for this!!

Do you have a docker-compose version as well?

[Bob-AFei]

Not yet, but it is quite simple to change the docker run command into docker-compose file.

[voplica-bot]

Hi @Bob-AFei thanks a lot for the container! Would you mind sharing your Dockerfile by any chance? I'm trying to build the Docker container will additional software installed and reuse this container as a base one: https://docs.nvidia.com/deeplearning/frameworks/pytorch-release-notes/rel-23-07.html
If you could share your Dockerfile it would be superb! Thank you so much!

[cgroovertech]

I'm having issues with the container.
Please see my logs:

Error setting up CodeFormer:
Traceback (most recent call last):
  File "/app/modules/codeformer_model.py", line 38, in setup_model
    from facelib.utils.face_restoration_helper import FaceRestoreHelper
  File "/app/repositories/CodeFormer/facelib/utils/face_restoration_helper.py", line 7, in <module>
    from facelib.detection import init_detection_model
  File "/app/repositories/CodeFormer/facelib/detection/__init__.py", line 10, in <module>
    from .retinaface.retinaface import RetinaFace
  File "/app/repositories/CodeFormer/facelib/detection/retinaface/retinaface.py", line 14, in <module>
    from basicsr.utils.misc import get_device
ImportError: cannot import name 'get_device' from 'basicsr.utils.misc' (/usr/local/lib/python3.10/site-packages/basicsr/utils/misc.py)
loading stable diffusion model: FileNotFoundError
Traceback (most recent call last):
  File "/app/webui.py", line 195, in initialize
    modules.sd_models.load_model()
  File "/app/modules/sd_models.py", line 431, in load_model
    sd_config = OmegaConf.load(checkpoint_config)
  File "/usr/local/lib/python3.10/site-packages/omegaconf/omegaconf.py", line 189, in load
    with io.open(os.path.abspath(file_), "r", encoding="utf-8") as f:
FileNotFoundError: [Errno 2] No such file or directory: '/app/configs/v1-inference.yaml'
Stable diffusion model failed to load, exiting
Loading weights [6ce0161689] from /app/models/Stable-diffusion/v1-5-pruned-emaonly.safetensors
Error setting up CodeFormer:
Traceback (most recent call last):
  File "/app/modules/codeformer_model.py", line 38, in setup_model
    from facelib.utils.face_restoration_helper import FaceRestoreHelper
  File "/app/repositories/CodeFormer/facelib/utils/face_restoration_helper.py", line 7, in <module>
    from facelib.detection import init_detection_model
  File "/app/repositories/CodeFormer/facelib/detection/__init__.py", line 10, in <module>
    from .retinaface.retinaface import RetinaFace
  File "/app/repositories/CodeFormer/facelib/detection/retinaface/retinaface.py", line 14, in <module>
    from basicsr.utils.misc import get_device
ImportError: cannot import name 'get_device' from 'basicsr.utils.misc' (/usr/local/lib/python3.10/site-packages/basicsr/utils/misc.py)
loading stable diffusion model: FileNotFoundError
Traceback (most recent call last):
  File "/app/webui.py", line 195, in initialize
    modules.sd_models.load_model()
  File "/app/modules/sd_models.py", line 431, in load_model
    sd_config = OmegaConf.load(checkpoint_config)
  File "/usr/local/lib/python3.10/site-packages/omegaconf/omegaconf.py", line 189, in load
    with io.open(os.path.abspath(file_), "r", encoding="utf-8") as f:
FileNotFoundError: [Errno 2] No such file or directory: '/app/configs/v1-inference.yaml'
Stable diffusion model failed to load, exiting
Loading weights [6ce0161689] from /app/models/Stable-diffusion/v1-5-pruned-emaonly.safetensors
Error setting up CodeFormer:
Traceback (most recent call last):
  File "/app/modules/codeformer_model.py", line 38, in setup_model
    from facelib.utils.face_restoration_helper import FaceRestoreHelper
  File "/app/repositories/CodeFormer/facelib/utils/face_restoration_helper.py", line 7, in <module>
    from facelib.detection import init_detection_model
  File "/app/repositories/CodeFormer/facelib/detection/__init__.py", line 10, in <module>
    from .retinaface.retinaface import RetinaFace
  File "/app/repositories/CodeFormer/facelib/detection/retinaface/retinaface.py", line 14, in <module>
    from basicsr.utils.misc import get_device
ImportError: cannot import name 'get_device' from 'basicsr.utils.misc' (/usr/local/lib/python3.10/site-packages/basicsr/utils/misc.py)
loading stable diffusion model: FileNotFoundError
Traceback (most recent call last):
  File "/app/webui.py", line 195, in initialize
    modules.sd_models.load_model()
  File "/app/modules/sd_models.py", line 431, in load_model
    sd_config = OmegaConf.load(checkpoint_config)
  File "/usr/local/lib/python3.10/site-packages/omegaconf/omegaconf.py", line 189, in load
    with io.open(os.path.abspath(file_), "r", encoding="utf-8") as f:
FileNotFoundError: [Errno 2] No such file or directory: '/app/configs/v1-inference.yaml'
Stable diffusion model failed to load, exiting
Loading weights [6ce0161689] from /app/models/Stable-diffusion/v1-5-pruned-emaonly.safetensors
Error setting up CodeFormer:
Traceback (most recent call last):
  File "/app/modules/codeformer_model.py", line 38, in setup_model
    from facelib.utils.face_restoration_helper import FaceRestoreHelper
  File "/app/repositories/CodeFormer/facelib/utils/face_restoration_helper.py", line 7, in <module>
    from facelib.detection import init_detection_model
  File "/app/repositories/CodeFormer/facelib/detection/__init__.py", line 10, in <module>
    from .retinaface.retinaface import RetinaFace
  File "/app/repositories/CodeFormer/facelib/detection/retinaface/retinaface.py", line 14, in <module>
    from basicsr.utils.misc import get_device
ImportError: cannot import name 'get_device' from 'basicsr.utils.misc' (/usr/local/lib/python3.10/site-packages/basicsr/utils/misc.py)
loading stable diffusion model: FileNotFoundError
Traceback (most recent call last):
  File "/app/webui.py", line 195, in initialize
    modules.sd_models.load_model()
  File "/app/modules/sd_models.py", line 431, in load_model
    sd_config = OmegaConf.load(checkpoint_config)
  File "/usr/local/lib/python3.10/site-packages/omegaconf/omegaconf.py", line 189, in load
    with io.open(os.path.abspath(file_), "r", encoding="utf-8") as f:
FileNotFoundError: [Errno 2] No such file or directory: '/app/configs/v1-inference.yaml'
Stable diffusion model failed to load, exiting
Loading weights [6ce0161689] from /app/models/Stable-diffusion/v1-5-pruned-emaonly.safetensors

[Bob-AFei]

It seems like the file '/app/configs/v1-inference.yaml' cannot be downloaded for some reasons. Here are two tips: 1.Please ensure your network is reachable, or use VPN if in you are in China mainland. 2. double check your file system is writable for docker