Skip to content

Latest commit

 

History

History
110 lines (86 loc) · 7.64 KB

README.md

File metadata and controls

110 lines (86 loc) · 7.64 KB
Raw

stable-diffusion-webui

CONTAINERS IMAGES RUN BUILD

This container has a default run command that will automatically start the webserver like this:

cd /opt/stable-diffusion-webui && python3 launch.py \
  --data=/data/models/stable-diffusion \
  --enable-insecure-extension-access \
  --xformers \
  --listen \
  --port=7860

After starting the container, you can navigate your browser to http://$IP_ADDRESS:7860 (substitute the address or hostname of your device). The server will automatically download the default model (stable-diffusion-1.5) during startup.

Other configuration arguments can be found at AUTOMATIC1111/stable-diffusion-webui/wiki/Command-Line-Arguments-and-Settings

  • --medvram (sacrifice some performance for low VRAM usage)
  • --lowvram (sacrafice a lot of speed for very low VRAM usage)

See the stable-diffusion container to run image generation from a script (txt2img.py) as opposed to the web UI.

Tips & Tricks

Negative prompts: https://huggingface.co/spaces/stabilityai/stable-diffusion/discussions/7857

Stable Diffusion XL

CONTAINERS
stable-diffusion-webui
   Builds stable-diffusion-webui_jp51 stable-diffusion-webui_jp60
   Requires L4T ['>=34.1.0']
   Dependencies build-essential cuda cudnn python numpy cmake onnx pytorch:2.2 torchvision huggingface_hub rust transformers xformers pycuda opencv tensorrt onnxruntime
   Dependants l4t-diffusion
   Dockerfile Dockerfile
   Images dustynv/stable-diffusion-webui:r35.2.1 (2024-02-02, 7.3GB)
dustynv/stable-diffusion-webui:r35.3.1 (2024-02-02, 7.3GB)
dustynv/stable-diffusion-webui:r35.4.1 (2024-02-02, 7.3GB)
dustynv/stable-diffusion-webui:r36.2.0 (2024-02-02, 8.9GB)
   Notes disabled on JetPack 4
CONTAINER IMAGES
Repository/Tag Date Arch Size
  dustynv/stable-diffusion-webui:r35.2.1 2024-02-02 arm64 7.3GB
  dustynv/stable-diffusion-webui:r35.3.1 2024-02-02 arm64 7.3GB
  dustynv/stable-diffusion-webui:r35.4.1 2024-02-02 arm64 7.3GB
  dustynv/stable-diffusion-webui:r36.2.0 2024-02-02 arm64 8.9GB

Container images are compatible with other minor versions of JetPack/L4T:
    • L4T R32.7 containers can run on other versions of L4T R32.7 (JetPack 4.6+)
    • L4T R35.x containers can run on other versions of L4T R35.x (JetPack 5.1+)

RUN CONTAINER

To start the container, you can use jetson-containers run and autotag, or manually put together a docker run command:

# automatically pull or build a compatible container image
jetson-containers run $(autotag stable-diffusion-webui)

# or explicitly specify one of the container images above
jetson-containers run dustynv/stable-diffusion-webui:r35.3.1

# or if using 'docker run' (specify image and mounts/ect)
sudo docker run --runtime nvidia -it --rm --network=host dustynv/stable-diffusion-webui:r35.3.1

jetson-containers run forwards arguments to docker run with some defaults added (like --runtime nvidia, mounts a /data cache, and detects devices)
autotag finds a container image that's compatible with your version of JetPack/L4T - either locally, pulled from a registry, or by building it.

To mount your own directories into the container, use the -v or --volume flags:

jetson-containers run -v /path/on/host:/path/in/container $(autotag stable-diffusion-webui)

To launch the container running a command, as opposed to an interactive shell:

jetson-containers run $(autotag stable-diffusion-webui) my_app --abc xyz

You can pass any options to it that you would to docker run, and it'll print out the full command that it constructs before executing it.

BUILD CONTAINER

If you use autotag as shown above, it'll ask to build the container for you if needed. To manually build it, first do the system setup, then run:

jetson-containers build stable-diffusion-webui

The dependencies from above will be built into the container, and it'll be tested during. Run it with --help for build options.