Go from docker pull; docker run; txt2img
on a Radeon ✨.
Provides a Dockerfile that packages the AUTOMATIC1111 fork Stable Diffusion WebUI repository, preconfigured with dependencies to run on AMD Radeon GPUs (particularly 5xxx/6xxx desktop-class GPUs) via AMD's ROCm platform.
First, pull the Docker image locally:
docker pull l1naforever/stable-diffusion-rocm:latest
Now, create an alias which will be used to run the Docker container. This normally goes in your ~/.zshrc
or ~/.bashrc
:
alias drun='docker run -it --network=host --device=/dev/kfd --device=/dev/dri --group-add=video --ipc=host --cap-add=SYS_PTRACE --security-opt seccomp=unconfined -v $(pwd):/pwd'
Finally, run the container:
drun --name stable-diffusion l1naforever/stable-diffusion-rocm:latest
After a period of downloading models and dependencies, you should see the output printed:
Running on local URL: http://localhost:7860/
Visit this URL in a browser to access the web UI.
Container fails to start with hipErrorNoBinaryForGpu: Unable to find code object for all current devices!
See issue #1. HIP's libraries bundled with the docker image are failing to load the right kernel for the specific GPU being used (this is particularly true with RX6xxx mobile variants). Try setting an environment variable to force HIP to use the gfx1030
kernel by passing the parameter -e HSA_OVERRIDE_GFX_VERSION=10.3.0
to docker run
, or updating the above drun
alias. For example:
alias drun='docker run -e HSA_OVERRIDE_GFX_VERSION=10.3.0 -it --network=host --device=/dev/kfd --device=/dev/dri --group-add=video --ipc=host --cap-add=SYS_PTRACE --security-opt seccomp=unconfined -v $(pwd):/pwd'