Sign inSign up

freeze1111/stable-diffusion-webui

By freeze1111

•Updated about 2 years ago

This is Unofficial image for Stable Diffusion web UI

Image
Machine learning & AI
3

3.3K

freeze1111/stable-diffusion-webui repository overview

⁠This is Unofficial image for Stable Diffusion web UI

Each tag is date (yyyymmdd) of checkout from :

https://github.com/AUTOMATIC1111/stable-diffusion-webui⁠

If you find any bugs or want to suggest some improvements, you can contact me at [email protected]

⁠How to use this

  1. You need an nvidia gpu (16xx, 20xx, 30xx, 40xx) with at least 4GB of memory.
  2. Install NVIDIA Container Toolkit (https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html⁠)
  3. Download some model (e.g. from https://civitai.com/models⁠)
  4. To run webui on port 8888 accessible from any (0.0.0.0) host IP use:
docker run --gpus all -it --rm -u $(id -u):$(id -g) -p=0.0.0.0:8888:7860 -v HOST_PATH_TO_SD_MODELS:/workspace/models/Stable-diffusion -v HOST_PATH_TO_OUTPUTS:/workspace/output freeze1111/stable-diffusion-webui:latest

⁠Dockerfile

FROM ubuntu:22.04

RUN apt-get update && apt-get install -y \ 
	git \
	python3 \
	python3-pip \
	python3-venv \
	ffmpeg \
	libsm6 \
	libxext6 \
	&& apt-get clean && rm -rf /var/lib/apt/lists/*

RUN mkdir /workspace
RUN useradd -ms /bin/bash user
RUN chown -R user:user /workspace
RUN chmod 755 /workspace
USER user

WORKDIR /workspace

RUN git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui.git .

RUN python3 -m venv venv/

RUN ./webui.sh --listen --exit --skip-torch-cuda-test --no-download-sd-model

# default command on start
CMD ["sh", "-c", "./webui.sh --listen --no-download-sd-model"]

Tag summary

Content type

Image

Digest

sha256:c7cccf7c1…

Size

5.5 GB

Last updated

about 2 years ago

docker pull freeze1111/stable-diffusion-webui