A simple way to install and use Stable Diffusion on your local computer. Provides a browser UI for generating images from text prompts. Just enter your text prompt, and see the generated image.

What does this do?

Two things:

1. Automatically downloads and installs Stable Diffusion on your local computer (no need to mess with conda or environments)
2. Gives you a simple browser-based UI to talk to your local Stable Diffusion. Enter text prompts and view the generated image. No API keys required.

All the processing will happen on your local computer, it does not transmit your prompts or process on any remote server.

System Requirements

1. Computer capable of running Stable Diffusion.
2. Linux or Windows 11 (with WSL) or Windows 10 v2004+ (Build 19041+) with WSL.
3. Requires (a) Docker, (b) docker-compose v1.29, and (c) nvidia-container-toolkit.

Important: If you're using Windows, please install docker inside your WSL's Linux. Install docker for the Linux distro in your WSL. Don't install Docker for Windows.

Installation

1. Clone this repository: git clone git@github.com:cmdr2/stable-diffusion-ui.git or download the zip file and unzip.
2. Open your terminal, and in the project directory run: docker-compose up & (warning: this will take some time during the first run, since it'll download Stable Diffusion's docker image, nearly 17 GiB)
3. Open http://localhost:8000 in your browser. That's it!

Usage

1. Open http://localhost:8000 in your browser (after running docker-compose up & from step 2 previously).
2. Enter a text prompt, like a photograph of an astronaut riding a horse in the textbox.
3. Press Make Image. This will take some time, depending on your system's processing power.
4. See the image generated using your prompt.

Please let me know if this worked (or didn't) for you! If you're getting errors, please check the Troubleshooting section below.

To stop the server, please run docker-compose down

Advanced Settings

You can also set the configuration like seed, width, height, num_outputs, num_inference_steps and guidance_scale using the 'show' button next to 'Advanced settings'.

Use the same seed number to get the same image for a certain prompt. This is useful for refining a prompt without losing the basic image design. Use a seed of -1 to get random images.

Troubleshooting

'./docker-compose.yml' is invalid:

ERROR: The Compose file './docker-compose.yml' is invalid because: services.stability-ai.deploy.resources.reservations value Additional properties are not allowed ('devices' was unexpected)

Please ensure you have docker-compose version 1.29 or higher. Check docker-compose --version, and if required update it to 1.29.

RuntimeError: Found no NVIDIA driver on your system:

If you have an NVIDIA GPU and the latest NVIDIA driver, please ensure that you've installed nvidia-container-toolkit.

Behind the scenes

This project is a quick way to get started with Stable Diffusion. You do not need to have Stable Diffusion already installed, and do not need any API keys. This project will automatically download Stable Diffusion's docker image, the first time it is run.

This project runs Stable Diffusion in a docker container behind the scenes, using Stable Diffusion's Docker image on replicate.com.

Bugs reports and code contributions welcome

This was built in a few hours for fun. So if there are any problems or suggestions, please feel free to file an issue or email me.

Also, please feel free to submit a pull request, if you have any code contributions in mind.

Disclaimer

I (and the authors of this project) are not responsible for any images generated using this interface.