LAVIS - A One-stop Library for Language-Vision Intelligence

OpenMMLab Multimodal Advanced, Generative, and Intelligent Creation Toolbox. Unlock the magic 🪄: Generative-AI (AIGC), easy-to-use APIs, awsome model zoo, diffusion models, for text-to-image genera…

Inpaint anything using Segment Anything and inpainting models.

VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.