The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Google Research

A simple screen parsing tool towards pure vision based GUI agent

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

StableLM: Stability AI Language Models

High-Resolution Image Synthesis with Latent Diffusion Models

PyTorch code and models for the DINOv2 self-supervised learning method.

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

🤖 💬 Deep learning for Text to Speech (Discussion forum: https://discourse.mozilla.org/c/tts)

🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022

Best Practices, code samples, and documentation for Computer Vision.

LLM-powered multiagent persona simulation for imagination enhancement and business insights.

A unified framework for 3D content generation.

Silero Models: pre-trained text-to-speech models made embarrassingly simple

Code repo for realtime multi-person pose estimation in CVPR'17 (Oral)

Easily train or fine-tune SOTA computer vision models with one open source training library. The home of Yolo-NAS.

An Open Source text-to-speech system built by inverting Whisper.

[ICCV 2019] Monocular depth estimation from a single image

[SIGGRAPH Asia 2022] VToonify: Controllable High-Resolution Portrait Video Style Transfer

A Production-ready Reinforcement Learning AI Agent Library brought by the Applied Reinforcement Learning team at Meta.

Incredibly fast Whisper-large-v3

[ICLR24] Official PyTorch Implementation of Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors

A high-fidelity 3D face reconstruction library from monocular RGB image(s)

Self-Supervised Learning of 3D Human Pose using Multi-view Geometry (CVPR2019)

[ECCV 2024] Tokenize Anything via Prompting

Joint deep network for feature line detection and description

Large dataset of hand-object contact, hand- and object-pose, and 2.9 M RGB-D grasp images.

Open Source LLM toolkit to build trustworthy LLM applications. TigerArmor (AI safety), TigerRAG (embedding, RAG), TigerTune (fine-tuning)

Low latency JSON generation using LLMs ⚡️

[ICCV 2019] Depth Hints are complementary depth suggestions which improve monocular depth estimation algorithms trained from stereo pairs