The official implementation of 3DDFA_V3 in CVPR2024 (Highlight).

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

[CVPR 2025] LION-FS: Fast & Slow Video-Language Thinker as Online Video Assistant

Any-length Video Inpainting and Editing with Plug-and-Play Context Control

Arbitrary-steps Image Super-resolution via Diffusion Inversion (CVPR 2025)

[CVPR 2024] This is the official source for our paper "SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis"

[AAAI 2025] MV-VTON: Multi-View Virtual Try-On with Diffusion Models

Fast State-of-the-Art Static Embeddings

Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.

"MiniRAG: Making RAG Simpler with Small and Free Language Models"

"LightRAG: Simple and Fast Retrieval-Augmented Generation"

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

How to build a Multi-Agentic Systems for RAG using LangGraph - Full project

❤️Emotional First Aid Dataset, 心理咨询问答、聊天机器人语料库

🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/mEkkMXFG

一个很小很小的RAG系统

Open AI Search, Support DeepResearch, DeepSeek R1, Ollama/LMStudio, SearXNG, Docker. AI搜索引擎，支持DeepResearch, 本地模型、深度思考模型（DeepSeek R1）、聚合搜索引擎SearXNG，支持Docker一键部署。

Jupyter notebooks that support my graph data science blog posts at https://bratanic-tomaz.medium.com/

Rethinking Step-by-step Visual Reasoning in LLMs

The official implementation of paper "BrushEdit: All-In-One Image Inpainting and Editing"

A reading list of video generation

Taming Stable Diffusion for Lip Sync!

A powerful tool that translates ComfyUI workflows into executable Python code.

肖像大师 中文版 comfyui-portrait-master

OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models

[CVPR2025] We present StableAnimator, the first end-to-end ID-preserving video diffusion framework, which synthesizes high-quality videos without any post-processing, conditioned on a reference ima…

[ICLR2025] DisPose: Disentangling Pose Guidance for Controllable Human Image Animation