A browser automation framework and ecosystem.

A generative AI-powered framework for testing virtual agents.

Clips AI is an open-source Python library that automatically converts long videos into clips.

💫 Toolkit to help you get started with Spec-Driven Development

Open-source, accurate and easy-to-use video speech recognition & clipping tool, LLM based AI clipping intergrated.

MCP server that interacts with Obsidian via the Obsidian rest API community plugin

Official implementation for "Blended Latent Diffusion" [SIGGRAPH 2023]

Lifting ControlNet for Generalized Depth Conditioning

[SIGGRAPH 2025] Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control

Open-source unified multimodal model

DeerFlow is a community-driven Deep Research framework, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community.

Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation".

Pytorch implementation of Twelve Labs' Video Foundation Model evaluation framework & open embeddings

[CVPR 2024] FRESCO: Spatial-Temporal Correspondence for Zero-Shot Video Translation

Official implementation of the ECCV paper "SwapAnything: Enabling Arbitrary Object Swapping in Personalized Visual Editing"

Open source software that helps you create and deploy high-frequency crypto trading bots

A Deep Research agent from scratch

Video datasets

Neural Approximate Mirror Maps for Constrained Diffusion Models (ICLR 2025)

Interactive visualizations of the geometric intuition behind diffusion models.

A general framework for inference-time scaling and steering of diffusion models with arbitrary rewards.

[AAAI 2025] DreamPhysics: Learning Physics-Based 3D Dynamics with Video Diffusion Priors

The simplest, fastest repository for training/finetuning small-sized VLMs.

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

EDM2 and Autoguidance -- Official PyTorch implementation

This repository contains a pure C++ ONNX implementation of multiple offline AI models, such as StableDiffusion (1.5 and XL), ControlNet, Midas, HED and OpenPose.

[ECCV 2024, Oral] DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors

[NeurIPS 2025] SpatialLM: Training Large Language Models for Structured Indoor Modeling