Setup

Make sure you have the latest version of docker installed

Download this repo and run:

docker compose --profile download up --build

This will download all of the required models / files, and validate their integrity.

Next, choose which UI you want to run:

hlky: The most popular fork, many features, with more on the way, sd-webui/stable-diffusion-webui
auto: Another great fork, many features with neat UI, AUTOMATIC1111/stable-diffusion-webui
auto-cpu: for users without a GPU.
lstein: One of the earliest forks, the UI is simple but has a lot of potential, lstein/stable-diffusion

After the download is done, you can run the UI using:

docker compose --profile [ui] up --build
# for example:
# docker compose --profile auto up --build
# or
# docker compose --profile hlky up --build

Note: the first start will take some time since other models will be downloaded, these will be cached in the cache folder, so next runs are faster.

If you face any problems, check the FAQ page, or create a new issue.

Download the models:

Put all of the downloaded files in the cache/models folder (create the folder if not there), it should look something like this:

cache/models/
├── model.ckpt
├── GFPGANv1.3.pth
├── RealESRGAN_x4plus.pth
├── RealESRGAN_x4plus_anime_6B.pth
├── LDSR.ckpt
└── LDSR.yaml