🔥🔥 UNO: A Universal Customization Method for Both Single and Multi-Subject Conditioning

VARGPT-v1.1: Improve Visual Autoregressive Large Unified Model via Iterative Instruction Tuning and Reinforcement Learning

[CVPR 2023] Official implementation of the paper "Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation"

Official repo for CFG-Zero*

🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org

Liquid: Language Models are Scalable and Unified Multi-modal Generators

Implementation of [CVPR 2025] "DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation"

🔥 InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity

Code Implementation of "PhotoDoodle: Learning Artistic Image Editing from Few-Shot Pairwise Data"

OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpainting

A GUI Agent application based on UI-TARS(Vision-Language Model) that allows you to control your computer using natural language.

[Arxiv'25] BlobCtrl: A Unified and Flexible Framework for Element-level Image Generation and Editing

A live stream development of RL tunning for LLM agents

Implementation of "EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer"

Code for SCIS-2025 Paper "UniAnimate: Taming Unified Video Diffusion Models for Consistent Human Image Animation".

🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation

No fortress, purely open ground. OpenManus is Coming.

Build production-ready AI agents in both Python and Typescript

Wan: Open and Advanced Large-Scale Video Generative Models

Build resilient language agents as graphs.

EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

Solve Visual Understanding with Reinforced VLMs

Lightweight framework for building Agents with memory, knowledge, tools and reasoning.

FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, le…

Video Generation Foundation Models: https://saiyan-world.github.io/goku/

🔥ICLR 2025 (Spotlight) One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt

An Agentic Deep Research Assistant similar to Gemini and OpenAI Deep Research

Magic to turn Cursor/Windsurf as 90% of Devin