macOS and AMD GPU Users
We highly recommend to Install InvokeAI locally using these instructions, because Docker containers can not access the GPU on macOS.
AMD GPU Users
Container support for AMD GPUs has been reported to work by the community, but has not received
extensive testing. Please make sure to set the
GPU_DRIVER=rocm environment variable (see below), and
build.sh script to build the image for this to take effect at build time.
Linux and Windows Users
For optimal performance, configure your Docker daemon to access your machine's GPU. Docker Desktop on Windows includes GPU support. Linux users should install and configure the NVIDIA Container Toolkit
They provide a flexible, reliable way to build and deploy InvokeAI. See Processes under the Twelve-Factor App methodology for details on why running applications in such a stateless fashion is important.
The container is configured for CUDA by default, but can be built to support AMD GPUs
by setting the
GPU_DRIVER=rocm environment variable at Docker image build time.
Developers on Apple silicon (M1/M2/M3): You can't access your GPU cores from Docker containers and performance is reduced compared with running it directly on macOS but for development purposes it's fine. Once you're done with development tasks on your laptop you can build for the target platform and architecture and deploy to another environment with NVIDIA GPUs on-premises or in the cloud.
This assumes properly configured Docker on Linux or Windows/WSL2. Read on for detailed customization options.
# docker compose commands should be run from the `docker` directory
docker compose up
Installation in a Linux container (desktop)#
Get a Huggingface-Token#
Besides the Docker Agent you will need an Account on huggingface.co.
After you succesfully registered your account, go to huggingface.co/settings/tokens, create a token and copy it, since you will need in for the next step.
Set up your environmnent variables. In the
docker directory, make a copy of
env.sample and name it
.env. Make changes as necessary.
Any environment variables supported by InvokeAI can be set here - please see the CONFIGURATION for further detail.
At a minimum, you might want to set the
INVOKEAI_ROOT environment variable
to point to the location where you wish to store your InvokeAI models, configuration, and outputs.
|Required - the location of your InvokeAI root directory. It will be created if it does not exist.
|InvokeAI will work without it, but some of the integrations with HuggingFace (like downloading from models from private repositories) may not work
|Optionally change this to
rocm to build the image for AMD GPUs. NOTE: Use the
build.sh script to build the image for this to take effect.
Build the Image#
Use the standard
docker compose build command from within the
If using an AMD GPU:
a: set the
GPU_DRIVER=rocm environment variable in
docker-compose.yml and continue using
docker compose build as usual, or
GPU_DRIVER=rocm in the
.env file and use the
build.sh script, provided for convenience
Run the Container#
Use the standard
docker compose up command, and generally the
docker compose CLI as usual.
Once the container starts up (and configures the InvokeAI root directory if this is a new installation), you can access InvokeAI at http://localhost:9090
Troubleshooting / FAQ#
- Q: I am running on Windows under WSL2, and am seeing a "no such file or directory" error.
- A: Your
docker-entrypoint.shfile likely has Windows (CRLF) as opposed to Unix (LF) line endings, and you may have cloned this repository before the issue was fixed. To solve this, please change the line endings in the
LF. You can do this in VSCode (
Ctrl+Pand search for "line endings"), or by using the
dos2unixutility in WSL. Finally, you may delete
git pull; git checkout docker/docker-entrypoint.shto reset the file to its most recent version. For more information on this issue, please see the Docker Desktop documentation
Created: September 9, 2022