leeguandong / Wav2lipAll
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。
☆18Updated 10 months ago
Alternatives and similar repositories for Wav2lipAll:
Users that are interested in Wav2lipAll are comparing it to the libraries listed below
- simple and fast wav2lip using onnx models for face-detection and inference. Easy installation☆25Updated 4 months ago
- 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☆62Updated 2 months ago
- wav2lip训练数据预处理综合工具☆40Updated last year
- ☆34Updated last year
- Just a suturing monster project.☆39Updated last year
- 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
- 基于大模型的高质量情感虚拟人系统(Gradio+FUNASR+ChatGLM2-6B+GPT-SOVITS+EAT+GFPGAN)☆24Updated 6 months ago
- ☆33Updated 2 years ago
- 基于MuseTalk的数字人代码。☆29Updated 5 months ago
- 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…☆51Updated 11 months ago
- ☆38Updated 2 weeks ago
- Simple and fast wav2lip using new 256x256 resolution trained onnx-converted model for inference. Easy installation☆39Updated 5 months ago
- ☆41Updated last year
- ☆11Updated 2 years ago
- ☆32Updated last month
- ☆27Updated last year
- 复现Wav2Lip作者新的论文☆20Updated last year
- optimized wav2lip☆19Updated last year
- ☆27Updated last year
- ☆49Updated last year
- ☆52Updated last year
- ☆24Updated 3 years ago
- ☆75Updated 4 months ago
- 基于roop与codeFormer的换脸一体脚本☆19Updated last week
- ☆50Updated last year
- Full version of wav2lip-onnx including face alignment and face enhancement and more...☆93Updated last month
- 基于DINet的推理服务,推理视频流和视频☆14Updated 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!☆22Updated 10 months ago
- 将Wav2Lip和GFPGAN进行结合实现高清数字人说话视频☆29Updated 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☆102Updated 11 months ago