All Algorithms implemented in Python

FastAPI framework, high performance, easy to learn, fast to code, ready for production

Robust Speech Recognition via Large-Scale Weak Supervision

Animation engine for explanatory math videos

CLI platform to experiment with codegen. Precursor to: https://lovable.dev

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.

🎨 Diagram as Code for prototyping cloud system architectures

Making large AI models cheaper, faster and more accessible

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Federated Query Engine for AI - The only MCP Server you'll ever need

We write your reusable computer vision tools. 💜

Official Code for DragGAN (SIGGRAPH 2023)

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

Data validation using Python type hints

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).

Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

YOLOv10: Real-Time End-to-End Object Detection [NeurIPS 2024]

A collaboration friendly studio for NeRFs

🐍 Geometric Computer Vision Library for Spatial AI

PyTorch3D is FAIR's library of reusable components for deep learning with 3D data

Code for the paper Hybrid Spectrogram and Waveform Source Separation

ImageBind One Embedding Space to Bind Them All

A collection of libraries to optimise AI model performances

[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"

DUSt3R: Geometric 3D Vision Made Easy

ECCV18 Workshops - Enhanced SRGAN. Champion PIRM Challenge on Perceptual Super-Resolution. The training codes are in BasicSR.