CXH

usechat. UseChat: local-first Computer Use runtime for WeChat agents

Comfyui_CSDMT_CXH. Python

Comfyui_CXH_GLM4. GLM4反推

Comfyui_CXH_Phi_3.5. Phi-3.5-vision-instruct fast talk with image

fpbrowser2api. fpbrowser2api插件框架-支持veo3.1、seedance2.0、omni flash、grok、nana banana、sora2、gpt-image2，QQ交流群：1035463132

ai-toolkit-perceptual. Python

SwiftI2V. [arXiv 2026] Project page for paper "SwiftI2V: Efficient High-Resolution Image-to-Video Generation via Conditional Segment-wise Generation"

ruyipage. 下一代Python的web自动化过检测框架，通过一切网站检测的Firefox内核浏览器。RuyiPage is a Python-based Firefox automation framework built on the next-generation WebDriver BiDi protocol.

hermes-agent. The agent that grows with you

Comfyui_RealRestorer. RealRestorer: Towards Generalizable Real-World Image Restoration with Large-Scale Image Editing Models

edict. 🏛️ 三省六部制 · OpenClaw Multi-Agent Orchestration System — 9 specialized AI agents with real-time dashboard, model config, and full audit trails

whaleclaw. Python

PocketAgent. Pocket Flow: 100-line LLM framework. Let Agents build Agents!

Prompt-Factory. AI Prompt Factory - Automated High-Quality Prompt Suite Generation After the system runs, various roles required by agents will be created, responsible for different functions! It's not a single prompt word, it's a complete set of agent prompt word engineering！！！！

SCAIL. SCAIL: Towards Studio-Grade Character Animation via In-Context Learning of 3D-Consistent Pose Representations (CVPR 2026 Findings)

EditThinker. Unlocking Iterative Reasoning for Any Image Editor

Gemini-API. ✨ Reverse-engineered Python API for Google Gemini web app

edit. Make changes to FMHY

scientific-agent-skills. Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 170,000+ scientists worldwide. 158 ready-to-use skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.

VideoX-Fun. 📹 A more flexible framework that can generate videos at any resolution and creates videos from images.

Z-Image. Python

WriteHERE. An Open-Source AI Writing Project.

TrendRadar. ⭐AI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts.🎯 告别信息过载，你的 AI 舆情监控助手与热点筛选工具！聚合多平台热点 + RSS 订阅，支持关键词精准筛选。AI 智能筛选新闻 + AI 翻译 + AI 分析简报直推手机，也支持接入 MCP 架构，赋能 AI 自然语言对话分析、情感洞察与趋势预测等。支持 Docker ，数据本地/云端自持。集成微信/飞书/钉钉/Telegram/邮件/ntfy/bark/slack 等渠道智能推送。

Jogg-Avatar. Python

zcf. Zero-Config Code Flow for Claude code & Codex

skills. Public repository for Agent Skills

nanochat. The best ChatGPT that $100 can buy.

VibeVoice. Open-Source Frontier Voice AI

Voost. [SIGGRAPH Asia 25] Voost: A Unified and Scalable Diffusion Transformer for Bidirectional Virtual Try-On and Try-Off

fantasy-talking2. [AAAI 2026] FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation

flymyai-lora-trainer. Qwen-Image text to image lora trainer

OmniVTON. [ICCV2025] OmniVTON: Training-Free Universal Virtual Try-On

UNIC-Adapter. Python

vscode-copilot-chat. Copilot Chat extension for VS Code

sm4llvton.

radial-attention. [NeurIPS 2025] Radial Attention: O(nlogn) Sparse Attention with Energy Decay for Long Video Generation

LoRAEdit. We achieves high-quality first-frame guided video editing given a reference image, while maintaining flexibility for incorporating additional reference conditions.

ObjectClear. [CVPR'26] ObjectClear: Precise Object and Effect Removal with Adaptive Target-Aware Attention

HunyuanVideo-Avatar. Python

magentic-ui. MagenticLite is an experimental agent that works across the browser and local file system

DreamO. [SIGGRAPH Asia 2025] DreamO: A Unified Framework for Image Customization

insert-anything. Python

VACE. [ICCV 2025] Official implementations for paper: VACE: All-in-One Video Creation and Editing

goku. [CVPR2025 Highlight] Video Generation Foundation Models: https://saiyan-world.github.io/goku/

BEN2_ComfyUI. Python

Hunyuan3D-2. High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

nautilus_trader. Production-grade Rust-native trading engine with deterministic event-driven architecture

T2ITrainer. Practice Code for text to image trainer

AgentLaboratory. Agent Laboratory is an end-to-end autonomous research workflow meant to assist you as the human researcher toward implementing your research ideas

TransPixeler. CVPR2025

NeuralSVG. Official implementation of NerualSVG

ComfyUI-TeaCache. Python

musubi-tuner. Python

SeleniumBase. 📊 APIs for web automation, testing, and bypassing bot-detection.

FaceLift. [ICCV 2025] FaceLift: Learning Generalizable Single Image 3D Face Reconstruction from Synthetic Heads

DJZ-Workflows. 1000+ ComfyUI workflows for AI image & video generation — Flux, SDXL, Hunyuan, CogVideo, upscaling, ControlNet & more

PAR. [CVPR2025 Highlight] PAR: Parallelized Autoregressive Visual Generation. https://yuqingwang1029.github.io/PAR-project

genesis-world. Simulation platform for general-purpose robotics & embodied AI learning.

prompt-poet. Streamlines and simplifies prompt design for both developers and non-technical users with a low code approach.

FitDiT. Official implementation of "FitDiT: Advancing the Authentic Garment Details for High-fidelity Virtual Try-on"

memo. [TMLR] Memory-Guided Diffusion for Expressive Talking Video Generation

Comfyui_Flux_Style_Adjust. Redux StyleModelApply adds more controls

xDiT. xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism

hotgo. HotGo 是AI 赋能企业级全栈前后端分离开发及移动应用基础平台，基于 Vue 和 GoFrame2.0 构建；内置 AI 开发规范、适配主流 AI 开发工具，人机协同高效开发。集成 jwt 鉴权、动态路由菜单、casbin 鉴权、消息队列、定时任务等功能，预置各类常用场景文件，助力专注业务开发。

ComfyUI_Prompt_Gallery. ComfyUI custom node that adds a quick and visual UI selector for building prompts to the sidebar.

ViewCrafter. [TPAMI 2025] ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis

MegaFusion. [WACV 2025] MegaFusion: Extend Diffusion Models towards Higher-resolution Image Generation without Further Tuning

ComfyUI-Dwpose-Tensorrt. Ultra fast dwpose estimation inside comfyui using tensorrt ⚡

CosmicMan. CosmicMan: A Text-to-Image Foundation Model for Humans (CVPR 2024)

Awesome-Efficient-AIGC. A list of papers, docs, codes about efficient AIGC. This repo is aimed to provide the info for efficient AIGC research, including language and vision, we are continuously improving the project. Welcome to PR the works (papers, repositories) that are missed by the repo.

ComfyUI_LayerStyle. A set of nodes for ComfyUI that can composite layer and mask to achieve Photoshop like functionality.

Comfyuinodes-HJGL.

ComfyUI-IC-Light. Using IC-LIght models in ComfyUI

BasicPBC. Official Implementation of "Learning Inclusion Matching for Animation Paint Bucket Colorization"

tri3d-comfyui-nodes. Python

Comfyui_CXH_DeepLX. DeepLX translate

sealos. Deploy real projects from GitHub or your AI coding agent, then keep them running with AI-powered operations.

FastGPT. 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, letting you easily develop and deploy complex question-answering systems without the need for extensive setup or configuration.

tabby. A terminal for a more modern age

GoodDrag. Ofiicial GoodDrag implementation.

VoiceCraft. Zero-Shot Speech Editing and Text-to-Speech in the Wild

ComfyUI_OOTDiffusion_CXH. OOTDiffusion

StableVITON. [CVPR2024] StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On

Comfyui-ergouzi-DGNJD. Python

OOTDiffusion. [AAAI 2025] Official implementation of "OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-on"

LWM. Large World Model -- Modeling Text and Video with Millions Context

Comfyui_segformer_b2_clothes. SegFormer model fine-tuned on ATR dataset for clothes segmentation but can also be used for human segmentation

Comfyui-Mine-PhotoMaker. Python

Comfyui_ALY. 自定义Comfyui节点

ComfyUI_Seg_VITON. comfyui-模特换装(Model dress up)

Comfyui_joytag. JoyTag is a state of the art AI vision model for tagging images, with a focus on sex positivity and inclusivity. It uses the Danbooru tagging schema, but works across a wide range of images, from hand drawn to photographic.

Legends-Of-Heroes. A battle of balls game, lol style, AI Agents base, support agent skills & unityMCP. 基于ET 10的双端C#游戏框架(.net10 + Unity2022.3.62, EUI+Luban+YooAsset)，包含战斗系统（技能/buff/行为树），内置LOL风格球球大战demo

Stable-diffusion-with-HR-VITON. 基于扩散模型stable diffusion的T恤图案设计和基于HR-VITON的虚拟试衣项目

InstantID. InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥

ControlNet. Let us control diffusion models!

ComfyUI-Gemini. Using Gemini in ComfyUI

Dlib. Dlib compiled binary (.whl) for python 3.7, 3.8, 3.9 for windows x64

EmotiVoice. EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine

HTFramework. Unity HTFramework, a rapid development framework of client based on Unity.

Umi-OCR. OCR software, free and offline. 开源、免费的离线OCR软件。支持截屏/批量导入图片，PDF文档识别，排除水印/页眉页脚，扫描/生成二维码。内置多国语言库。

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

LucidDreamer. Official code for the paper "LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenes".

ComfyUI-extension-tutorials.

VideoCrafter. VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models

UnityWebGL-LoadingTest. Unity WebGL platform and version comparisons with a lot of nice extras

ComfyUI_IPAdapter_plus. Python

upscayl. 🆙 Upscayl - #1 Free and Open Source AI Image Upscaler for Linux, MacOS and Windows.

facefusion. Industry leading face manipulation platform

video_summarize. video_summarize（视频总结：上传视频通过prompt对视频内容经行总结输出）

CodeFormer. [NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer

AI-. AI视频创作，开发使用python支持多国语音配音，ffmpeg+openai-whisper+tts，项目仅作参考,技术探讨研究，拒绝非法使用

SalesGPT. Context-aware AI Sales Agent to automate sales outreach.

BiLLa. BiLLa: A Bilingual LLaMA with Enhanced Reasoning Ability

FastChat. An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

lawyer-llama. 中文法律LLaMA (LLaMA for Chinese legel domain)

SadTalker-Video-Lip-Sync. 本项目基于SadTalkers实现视频唇形合成的Wav2lip。通过以视频文件方式进行语音驱动生成唇形，设置面部区域可配置的增强方式进行合成唇形（人脸）区域画面增强，提高生成唇形的清晰度。使用DAIN 插帧的DL算法对生成视频进行补帧，补充帧间合成唇形的动作过渡，使合成的唇形更为流畅、真实以及自然。

FinalFramework. 为独立游戏而生，Gameplay热更新游戏框架。（对初学者不友好）

SysMocap. A real-time motion capture system for 3D virtual character animating.

DigiHuman. Automatic 3D Character animation using Pose Estimation and Landmark Generation techniques

UnityHandTrackingWithMediapipe. Realtime hand tracking and finger tracking in Unity using Mediapipe

VRigUnity. VRM hand tracking using mediapipe

MediaPipeUnityPlugin. Unity plugin to run MediaPipe

web3.unity. 🕹 Unity SDK for building games that interact with blockchains.

JSSDK-Demo. JSSDK Demo

singo. A simple Go web service starter for building RESTful APIs with Gin, GORM, Redis, sessions, i18n, and API tests.