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
☆69Updated 4 months ago
Alternatives and similar repositories for stream-wav2lip:
Users that are interested in stream-wav2lip are comparing it to the libraries listed below
- ☆41Updated last year
- ☆39Updated 2 months ago
- Just a suturing monster project.☆40Updated last year
- ☆38Updated last week
- ☆219Updated last year
- Simple and fast wav2lip using new 256x256 resolution trained onnx-converted model for inference. Easy installation☆38Updated 6 months ago
- wav2lip384生成器网格权重——来自不蠢不蠢☆81Updated last month
- 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…☆52Updated last year
- Full version of wav2lip-onnx including face alignment and face enhancement and more...☆97Updated 2 months ago
- ☆74Updated 6 months ago
- Considering the original Wav2Lip was trained on LSR2 and didn't have good performance on Chinese. I preprocessed CMLR Dataset and would t…☆60Updated last year
- ☆35Updated last year
- ☆51Updated last year
- wav2lip训练数据预处理综合工具☆40Updated last year
- A docker free offline version for HeyGem; Python and Linux is all you need!☆151Updated last week
- 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☆103Updated last year
- ☆34Updated 2 years ago
- ☆50Updated 3 months ago
- ☆32Updated 2 months ago
- 基于MuseTalk的数字人代码。☆29Updated 7 months ago
- 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☆162Updated 6 months ago
- 这是一个在wav2lip，使用wav2lip、gfpgan、yolov5等模型用RT加速的超快推理！经测试在2070显卡上可达到0.03秒每帧实现实时推理。☆27Updated last year
- ☆247Updated last week
- 在DH_live项目基础上修改，添加webui界面☆60Updated 5 months ago
- python库，实现推送实时rtmp音视频流☆117Updated last year
- ☆50Updated last year
- ☆52Updated last year
- 主要写er-nerf从零到一所有部署过程☆44Updated 7 months ago
- 将Wav2Lip和GFPGAN进行结合实现高清数字人说话视频☆30Updated last year
- ☆199Updated last year