Stars
AI-powered interactive 3D model generation, inspection, and presentation studio.
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
An agentic skills framework & software development methodology that works.
模型推理云平台产品方案 — 从功能设计、系统架构到技术选型的一站式规划文档。Model Inference Cloud Platform — a complete product plan covering feature design, system architecture, and technology selection.
Run, manage, and scale AI workloads on any AI infrastructure. Use one system to access & manage all AI compute (Kubernetes, Slurm, 20+ clouds, on-prem).
The best-benchmarked open-source AI memory system. And it's free.
Get your documents ready for gen AI
你想蒸馏的下一个员工，何必是同事。蒸馏任何人的思维方式——心智模型、决策启发式、表达DNA。Distill how anyone thinks.
♾️ 开源数字永生框架 — 从聊天记录蒸馏任何人的七维数字分身。支持微信/飞书/iMessage/Telegram等12+平台，7种角色模板，对齐 OpenClaw Soul Spec 标准。一行指令让你的AI学会蒸馏。
Try X-Dub to sync any character in a video with any audio you like | Official repository for "From Inpainting to Editing: Unlocking Robust Mask-Free Visual Dubbing via Generative Bootstrapping"
xModelFactory 是一个面向大语言模型与多模态模型训练的模块化框架，提供预训练、微调、偏好优化和多卡训练等完整能力
🎓 Update Talking-Face Research Papers Daily
Foundation Models and Data for Human-Human and Human-AI interactions.
SoulX-FlashHead: A unified 1.3B-parameter framework designed for high-fidelity, infinite-length, and real-time streaming portrait video generation.
Turn paper/text/topic into editable research figures, technical route diagrams, and presentation slides.
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
rCM & Causal-rCM: Best Algorithms/Infrastructures for Bidirectional/Autoregressive Video Diffusion Distillation at Scale
[CVPR 2026] PersonaLive! : Expressive Portrait Image Animation for Live Streaming
Create Assets from Video. Transform your video into a professional production package. Automated shot lists, color scripts, screenplays, and posters—all powered by AI.
Unlimited-length talking video generation that supports image-to-video and video-to-video generation
GMTalker 由光明实验室媒体智能团队打造的3d数字人。系统集成了语音识别、语音合成、自然语言理解、嘴型动画驱动。支持windows、Linux、安卓快速部署。
We present StableAvatar, the first end-to-end video diffusion transformer, which synthesizes infinite-length high-quality audio-driven avatar videos without any post-processing, conditioned on a re…
Official implementation of "Sonic: Shifting Focus to Global Audio Perception in Portrait Animation"
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
[NeurIPS 2025] Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation