Featured demo
SeamlessExpressive demo
Try the SeamlessExpressive demo to hear how you sound in a different language while maintaining elements of your expression and tone.
View demoDemos
Computer vision
Segment Anything Model (SAM)
The new Segment Anything Model (SAM) is a promptable segmentation system with zero-shot generalization to unfamiliar objects and images, that has no need for additional training.
Computer vision
DINOv2
A family of models producing universal features suitable for image-level visual tasks as well as pixel-level visual tasks.
Computer vision
DINO
Computer vision powered by self-supervised learning to build highly efficient systems that perform well with less labeled data.
Computer vision
Animated Drawings
A first-of-its-kind method for using AI to animate amateur drawings
Metagenomics
ESM Metagenomic Atlas
An open atlas of 772 million predicted metagenomic protein structures
Machine translation
No Language Left Behind
Stories Told Through Translation: books from around the world translated into hundreds of languages with the NLLB-200 model.
Frameworks and tools
Sharing our ML frameworks and tools with the community to collaborate and accelerate AI advancement
Models and Libraries
Our open-sourced libraries and models for those taking our AI learnings further through software and app development
Datasets
Large-scale datasets and benchmarks for training, evaluating, and testing models to measure and advance AI progress
System cards
Multiple machine learning (ML) models that help people understand the intention, impact and limitations of our AI systems
Publications
Our library of published papers to learn about our latest AI breakthroughs and innovations
Who We Are
Our Actions
Newsletter
Meta © 2023