liveportrait

Open-source, local-first video editor where creators and AI agents edit the same real timeline.

gradio WebUI for AdvancedLivePortrait

LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control

LiveTalk is a unified, high-performance talking head generation system that combines the power of LivePortrait and MuseTalk open-source repositories. The PyTorch models from these projects have been ported to ONNX format and optimized for CoreML to enable efficient on-device inference in Unity.

Run LivePortrait on Replicate

使用onnxruntime部署LivePortrait人像动画生成，包含C++和Python两个版本的程序

Unofficial One-click Version of LivePortrait, with Webcam Support

一个《原神》AI驱动视频项目，利用LLM API生成角色互动文案，VITS技术进行语音合成，并结合先进的文生图和视频合成技术，创造出游戏角色之间有趣的场景。最终产出为短视频。

sd webui (forge) extension for AdvancedLivePortrait

End-to-end AI digital-human live-streaming platform: create avatars (image / Edge-TTS voice / persona) → LivePortrait base video → Edge-TTS + Wav2Lip lip-sync → DeepSeek LLM live replies → SRS streaming + Next.js viewer. Built with Go (Gin), MariaDB, Redis, RustFS, Docker, and a Python (uv) AI worker (macOS MPS / Linux CUDA / AMD ROCm).

Ultra-Realistic Portrait Animation Studio Transform still portraits into lifelike, animated videos using the power of AI. PresentaPulse combines LivePortrait for sophisticated facial animation and Real-ESRGAN for video enhancement, all within a sleek, feature-packed desktop application.

OliveWolf — 开源3D数字人引擎: LHM(全身3D)+LivePortrait(2D头肩)双后端, 实时音频驱动问答, 企业级部署. A Miraphant product.

Docker image for LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control

Local-first macOS workspace for GFPGAN portrait restoration and consent-based LivePortrait animation.

LivePortrait表情转移对口型软件免安装一键启动整合包

SOTA Text-to-Video Generator with MuseTalk 1.5, LivePortrait, and LTX-Video. Cinema-grade lip-sync and animation.

Style-Talking is a zero-shot audio-driven digital human system for cloning speaking style from a reference video.

面向 16GB 显存设备的 AI 陪伴项目：自定义角色、语音聊天、情绪表情与口型视频。React + Node.js + Python，结合 DeepSeek、火山引擎、LivePortrait 与 MuseTalk，探索从一句话到数字人回应的完整流程。

Plugin-free, deterministic TensorRT-10 warp for LivePortrait & FasterLivePortrait. Fixes face deformation/melting and black-frame under GPU contention (the non-deterministic grid_sample_3d plugin), and unblocks TensorRT 10. Drop-in, ~25% faster.

本地数字人视频工坊：用自己的视频/照片 + 声音工坊克隆的声音（普通话/粤语）生成口型同步视频；MuseTalk / LatentSync / JoyVASA，面向 8GB 显卡，可导出剪映草稿