I wanted to share a new Python package called FastQL that makes it easy to prototype and share machine learning models using GraphQL. It's really fast and efficient thanks to using rust to serve the API on a separate process. With FastQL, all you have to do is provide a callback function and a Python dictionary describing your GraphQL API, and FastQL will handle the rest. This makes it super easy to prototype ML models and get them up and running quickly. You can find FastQL on PyPI and GitHub. We've included simple steps and a Dockerfile to help you spin up your own Stable Diffusion or other Hugging Face models. There's even an example that lets you train a huggingface diffusers (Stable diffusion 2, runway) model on your own images, with instructions for spinning it up on AWS in minutes, even if you're new to ML and Python. We'd love to have your help and support, so if you're interested in getting involved, let us know! Thanks to Async-GraphQL, Hugging Face, Stable Diffusion, and all the other people and projects that inspired and helped us. DJ Fresh, @chrisjbishop156 and friends.