emptysoal / VideoRestoreLinks
Enhance video resolution
☆32Updated 2 years ago
Alternatives and similar repositories for VideoRestore
Users that are interested in VideoRestore 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☆167Updated 9 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☆75Updated 7 months ago
- 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☆105Updated last year
- Erase specific content from the video that you don't wanna see☆305Updated 2 years ago
- Realtime Video and Audio Streaming with WebRTC and Gradio☆57Updated 3 weeks ago
- Simple and fast wav2lip using new 256x256 resolution trained onnx-converted model for inference. Easy installation☆42Updated 9 months ago
- ☆75Updated 9 months ago
- 基于DCT-Net的图片/视频转绘gradio界面webui☆26Updated last year
- ☆33Updated 5 months ago
- ☆52Updated 2 years ago
- 当下热门的模糊人脸修复模型的部署,分别是:Codeformer,GFPGAN,GPEN,Restoreformer☆34Updated last year
- ☆43Updated this week
- 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 last year
- ☆41Updated last year
- ☆35Updated 2 years ago
- 基于roop与codeFormer的换脸一体脚本☆21Updated 3 months ago
- ☆58Updated last year
- simple and fast wav2lip using onnx models for face-detection and inference. Easy installation☆25Updated 9 months ago
- wav2lip训练数据预处理综合工具☆40Updated last year
- 基于MuseTalk的数字人代码。☆30Updated 10 months ago
- Just a suturing monster project.☆41Updated last year
- 主要写er-nerf从零到一所有部署过程☆43Updated 10 months ago
- ☆199Updated 2 years ago
- A docker free offline version for HeyGem; Python and Linux is all you need!☆289Updated 2 months ago
- This is the onnxruntime inference code for GFP-GAN: Towards Real-World Blind Face Restoration with Generative Facial Prior (CVPR 2021). …☆148Updated 2 years ago
- 基于 NSFW Model 色情图片识别鉴黄 后面更新视频检测☆29Updated 3 years 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。☆29Updated 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…☆55Updated last year
- ☆231Updated last year
- ☆41Updated last year