Alternatives and similar repositories for metahuman-stream

Users that are interested in metahuman-stream are comparing it to the libraries listed below

• langzizhixin / IP_LAP_GFPGAN
  ☆33Updated 11 months ago
• HumanAIGC / chat-anyone
  project page for ChatAnyone
  ☆115Updated 9 months ago
• langzizhixin / wav2lip-576x576
  This is a project about talking faces. We use 576X576 sized facial images for training, which can generate 2k, 4k, 6k, and 8k digital hum…
  ☆55Updated last year
• IronSpiderMan / MuseTalkPlus
  基于MuseTalk的数字人代码。
  ☆34Updated last year
• ECNU-CILAB / DiffutoonProjectPage
  The project page of Diffutoon
  ☆28Updated last year
• foxyear-kyumin / lip_mask
  通过此代码可以免训练模型并通过轻量级服务器定制数字人形象
  ☆106Updated last year
• chengyuanba / avatar_ernerf
  Just a suturing monster project.
  ☆42Updated 2 years ago
• zhangnn520 / my_sadtalker
  ☆20Updated last year
• zhangbo2008 / wav2lip384_my2
  ☆42Updated 2 years ago
• bjfrbjx / stream-wav2lip
  优化wav2lip的执行步骤，将头脸分离、嘴型替换、回补背景三个步骤分离，添加gfpgan强化面部功能，实现提前解帧，流式循环处理，对接obs
  ☆81Updated last year
• aigc3d / LAM_Audio2Expression
  Generate ARKit expression from audio in realtime
  ☆175Updated 2 months ago
• lakysir / aimh8_digital_human
  私有化自动数字人排队训练、短视频排队生成的微信小程序、web运营后台管理系统一键部署，基于单人训练的音频驱动唇形，比wav2lip、deepfacelab、liveportrait、musetalk等等唇形方案更好，直接可以商业化，支持中日英韩多种语音复刻
  ☆54Updated 8 months ago
• mco2004 / qwen-tts
  Qwen-TTS offers a robust voice synthesis service using FastAPI, supporting bilingual and dialect options. Explore seamless audio generati…
  ☆108Updated this week
• oneCodeSuperman / LstmSync
  开源的LstmSync数字人泛化模型，只做最好的泛化模型！
  ☆135Updated this week
• HumanAIGC-Engineering / gradio-webrtc
  Realtime Video and Audio Streaming with WebRTC and Gradio
  ☆75Updated 6 months ago
• langzizhixin / Double_Talker
  ☆58Updated 2 years ago
• HassanMuhammadSannaullah / Wav2lip-Fix-For-Inference
  This project fixes the Wav2Lip project so that it can run on Python 3.9. Wav2Lip is a project that can be used to lip-sync videos to audi…
  ☆17Updated 2 years ago
• xxyQwQ / ComfyBench
  Implementation for the paper "ComfyBench: Benchmarking LLM-based Agents in ComfyUI for Autonomously Designing Collaborative AI Systems".
  ☆197Updated 2 weeks ago
• langzizhixin / lil
  ☆51Updated 2 years ago
• Soul-AILab / SoulX-FlashTalk
  SoulX-FlashTalk is the first 14B model to achieve a sub-second start-up latency (0.87s) while sustaining a real-time throughput of 32 FPS
  ☆72Updated last week
• rogerle / wav2lip_train
  ☆35Updated 2 years ago
• Virtu-Lab / DreamVVT
  DreamVVT: Mastering Realistic Video Virtual Try-On in the Wild via a Stage-Wise Diffusion Transformer Framework
  ☆141Updated 5 months ago
• whitebaby / IP-Adapter-FaceID-demo
  IP Adapter FaceID demo webui
  ☆20Updated 2 years ago
• Aria-Zhangjl / StoryWeaver
  [AAAI 2025] StoryWeaver: A Unified World Model for Knowledge-Enhanced Story Character Customization
  ☆224Updated 8 months ago
• zvxme / wav2lip_chinese
  ☆75Updated last year
• Ikaros-521 / digital_human_video_player
  洛曦 数字人视频播放器，带HTTP API，使用gradio api对接Easy-Wav2Lip、Sadtalker、GeneFacePlusPlus、MuseTalk，也可以用于播放本地视频
  ☆175Updated last year
• Ikaros-521 / xuniren
  虚拟人说话头生成(NeRF虚拟人实时驱动) 含API
  ☆15Updated 2 years ago
• vivoCameraResearch / Magic-TryOn
  MagicTryOn is a video virtual try-on framework based on a large-scale video diffusion Transformer.
  ☆495Updated 2 weeks ago
• jdh-algo / JoyHallo
  JoyHallo: Digital human model for Mandarin
  ☆521Updated 3 months ago
• HumanAIGC / lite-avatar
  ☆406Updated 6 months ago