awesome-tiny-sd

Tiny stable diffusion chatbot based on segmind/small-sd to generate images upon text prompts.

View the Project on GitHub AstraBert/awesome-tiny-sd

GitHub top language GitHub commit activity Static Badge Static Badge Static Badge Static Badge

Ernesto, a mutant cat generated by awesome-tiny-sd, welcomes you to this pagešŸ¤­... Click on it, you won't be disappointed

awesome-tiny-sd

Run a stable diffusion model limitless, generate as many images as you want, free your fantasy!šŸ 

FundingšŸ„ŗ

Please consider to support this project and its author, Astra Bertelli, by sponsoring on GitHub: if enough people sponsor this project, weā€™ll be able to get to a GPU-powered Hugging Face space, to speed up image generation and unleash the true potential of awesome-tiny-sd!

Overview

Tiny stable diffusion chatbot based on segmind/small-sd to generate image upon text prompts.

Try it on Hugging Face Spaces:

Here is an example chat:

example_chat

Run awesome-tiny-sd locally

You can run awesome-tiny-sd locally through its Docker image:

docker pull ghcr.io/astrabert/awesome-tiny-sd:latest
docker run -p 7860:7860 ghcr.io/astrabert/awesome-tiny-sd:latest

IMPORTANT NOTE: running the app within docker run does not log the port on which the app is running until you press Ctrl+C, but in that moment it also interrupt the execution! The app will run on port 0.0.0.0:7860 (or localhost:7860 if your browser is Windows-based), so just make sure to open your browser on that port and to refresh it after 1 to 5 mins (depending on your computer and network capacities), when the model and the tokenizer should be loaded and the app should be ready to work!

Another fundamental caveat is that we are dealing here with a relatively small stable-diffusion model (approx. 3GB), so the it is CPU-friendly (you can run it GPUless): to make the docker container work, indeed, 8GB RAM + 12 cores CPU can be enough, but image generation will be really slow.

You will need at least 16 to 32 GB RAM and/or a GPU to speed up the model.

Troubleshooting

Upcoming featuresšŸš€

Contributing

Contributions are welcome! If you would like to improve the chatbotā€™s functionality or add new features, please fork the repository and submit a pull request.

References

License

This project is licensed under MIT License.

If you use this work for your projects, please consider citing the author Astra Bertelli.