lakysir / aimh8_digital_humanLinks
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
☆56Updated 9 months ago
Alternatives and similar repositories for aimh8_digital_human
Users that are interested in aimh8_digital_human are comparing it to the libraries listed below
Sorting:
- 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
- The fastest digital human algorithm, now on your desktop.☆568Updated 4 months ago
- 开源的LstmSync数字人泛化模型,只做最好的泛化模型!☆139Updated last week
- 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
- 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
- ☆416Updated 7 months ago
- wav2lip384生成器网格权重——来自不蠢不蠢☆145Updated 10 months ago
- project page for ChatAnyone☆116Updated 10 months ago
- ☆42Updated 2 years ago
- 基于MuseTalk的数字人代码。☆35Updated last year
- A docker free offline version for HeyGem; Python and Linux is all you need!☆417Updated 3 weeks ago
- 一个用于CosyVoice的api接口项目☆334Updated 5 months ago
- 在DH_live项目基础上修改,添加webui界面☆73Updated 9 months ago
- JoyHallo: Digital human model for Mandarin☆522Updated 4 months ago
- [NeurIPS 2025] OmniTalker: Real-Time Text-Driven Talking Head Generation with In-Context Audio-Visual Style Replication☆417Updated 4 months ago
- CosyVoice2 功能扩充(预训练音色推理/3s极速复刻/自然语言控制/自动识别/音色模型保存/API)☆188Updated 10 months ago
- ☆82Updated 6 months ago
- video to video translation with voice clone and lip synchronization|带有语音克隆和口型同步的视频翻译,支持中英互换☆144Updated last year
- python库,实现推送实时rtmp音视频流☆136Updated last year
- Windows不用搭建环境只要英伟达显卡就行,4G显存仅需,解压即用!☆26Updated last year
- Real time streaming talking head☆480Updated last year
- 将Wav2Lip和GFPGAN进行结合实现高清数字人说话视频☆37Updated 8 months ago
- 10000 chatTTS voices !chatTTS 音色库,再也不为音色抽卡烦恼啦。这是我第一个项目,熬夜龟速生产10000条音色并上传Github,给点鼓励呗哈!主域名:https://www.TTSlist.com 备用:http://ttslist.aiqb…☆214Updated last year
- Just a suturing monster project.☆42Updated 2 years ago
- 基于wav2lip进行虚拟数字人训练,唇形驱动,包括数据处理流程等,模型包括96x96,192x192,192x288,288x288。☆22Updated last year
- Extension of ChatTTS, 3x Faster on Windows, Support Voice Cloning and Mobile Deployment☆172Updated 11 months ago
- [真诚套壳]东半球最强的套壳数字人系统,前后端分离,可对接硅基、飞影、闪剪、壹定开放平台等所有市面上的数字人API接口,开箱即用,star交个朋友。☆100Updated last year
- Realtime Video and Audio Streaming with WebRTC and Gradio☆76Updated 7 months ago
- 基于DCT-Net的图片/视频转绘gradio界面webui☆27Updated last year
- 数字人训练☆20Updated 2 years ago