Official code for our ICCV2025 paper "SDMatte: Grafting Diffusion Models for Interactive Matting"

Python library for building and running distributed data pipelines using Ray

An open-source application for building, observing, and collaborating with teams of AI agents.

A fast AI Video Generator for the GPU Poor. Supports Wan 2.1/2.2, Qwen Image, Hunyuan Video, LTX Video and Flux.

Kanban board to manage your AI coding agents

A LLM trained only on data from certain time periods to reduce modern bias

Lumos Project: Frontier video unified model research by Alibaba DAMO Academy.

H-Net: Hierarchical Network with Dynamic Chunking

PyTorch Code for Energy-Based Transformers paper -- generalizable reasoning and scalable learning

OCRFlux is a lightweight yet powerful multimodal toolkit that significantly advances PDF-to-Markdown conversion, excelling in complex layout handling, complicated table parsing and cross-page conte…

The implementation of Extreme Viewpoint 4D Video Generation

A powerful GUI app and Toolkit for Claude Code - Create custom agents, manage interactive Claude Code sessions, run secure background agents, and more.

A ComfyUI node for driving videos using batches of images.

UICrit is a dataset containing human-generated natural language design critiques, corresponding bounding boxes for each critique, and design quality ratings for 1,000 mobile UIs from RICO. This dat…

Official code for PLoP

A TypeScript library for coordinating communication between multiple agents using the Model Context Protocol (MCP)

[ICLR 2025] Official implementation of "DiffSplat: Repurposing Image Diffusion Models for Scalable 3D Gaussian Splat Generation".

An open-source AI agent that brings the power of Gemini directly into your terminal.

OmniGen2: Exploration to Advanced Multimodal Generation.

Refine high-quality datasets and visual AI models

[ICCV 2025] Official implementation of the paper "DreamCube: 3D Panorama Generation via Multi-plane Synchronization".

An open-source implementation of Regional Adaptive Sampling (RAS), a novel diffusion model sampling strategy that introduces regional variability in sampling steps

The official code repository for SongBloom: Coherent Song Generation via Interleaved Autoregressive Sketching and Diffusion Refinement

Get your documents ready for gen AI

ComfyUI nodes for Lotus depth/normal prediction

Official implementation of Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction

Bend2 - WIP

ObjectClear: Complete Object Removal via Object-Effect Attention