Ikaros-521 / xuniren
虚拟人说话头生成(NeRF虚拟人实时驱动) 含API
☆15Updated last year
Alternatives and similar repositories for xuniren:
Users that are interested in xuniren are comparing it to the libraries listed below
- Just a suturing monster project.☆39Updated last year
- ☆45Updated 10 months ago
- ☆33Updated 2 years ago
- 基于MuseTalk的数字人代码。☆29Updated 6 months ago
- ☆32Updated last month
- ☆75Updated 5 months ago
- Simple and fast wav2lip using new 256x256 resolution trained onnx-converted model for inference. Easy installation☆39Updated 5 months ago
- make your charactor Dancing as Native style☆40Updated last year
- 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☆66Updated 3 months ago
- wav2lip训练数据预处理综合工具☆40Updated last year
- ☆50Updated last year
- ☆42Updated 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☆103Updated last year
- ☆41Updated last year
- Full version of wav2lip-onnx including face alignment and face enhancement and more...☆93Updated last month
- FaceChain is a deep-learning toolchain for generating your Digital-Twin.☆47Updated last year
- 基于DCT-Net的图片/视频转绘gradio界面webui☆25Updated 9 months ago
- ☆52Updated last year
- 跨语种语音克隆,中文版Webui☆51Updated last year
- 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 last year
- Installable version of oms-Diffusion☆27Updated last year
- ☆176Updated last month
- 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☆163Updated 5 months ago
- ☆50Updated last year
- ☆34Updated last year
- simple and fast wav2lip using onnx models for face-detection and inference. Easy installation☆25Updated 5 months ago
- Comfyui custom node for FunAudioLLM include CosyVoice and SenseVoice☆76Updated 4 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
- 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。☆19Updated 10 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