We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Real image inversion via Segments

Stable Diffusion is a latent text-to-image diffusion model capable of generating photo-realistic images.

imgproxy: fast and secure on-the-fly image processing.

Refactor, understand, and write code effortlessly using Cursor's AI source editor.

The first platform built for prompt engineers. Maintain a log of your prompts and OpenAI API requests. Track, debug, and replay old completions.

The Dreambooth Ion Cannon is a repository that abstracts away a large chunk of the execution pain points of The Repo Formerly Known As Dreambooth, providing a layperson an easily accessible guide to uploading images, training a Stable Diffusion model on said images, and generating new images according to pre-selected prompts.

The ultimate PyTorch research framework. Scale your models, without the boilerplate.

Colab notebooks demonstrating prompt-based music generation via Mubert API.