LeeeLiu / SpeedUpVideoCapLinks
面部表情捕捉。输入2D人脸，输出3D几何动画。
☆23Updated 3 years ago
Alternatives and similar repositories for SpeedUpVideoCap
Users that are interested in SpeedUpVideoCap are comparing it to the libraries listed below
Sorting:
- fast_faceswap use dlib and change_style_network（基于dlib和风格迁移网络的快速换脸）☆10Updated 6 years ago
- Mirror : a maya facial capture animation toolkit based on mediapipe☆22Updated 3 years ago
- 本次开源为DL-B，是一个基于ChatGLM、Wav2Lip、So-VITS组建的数字形象方案。可以在此基础之上增加其他组件达到数字生命的效果。This open source is DL-B, which is a digital image scheme based o…☆107Updated 2 years ago
- Простое WebUI на Flask для EasyWav2Lip☆27Updated last year
- PSGAN running with ncnn⚡妆容迁移/仿妆⚡Imitation Makeup/Makeup Transfer⚡☆194Updated 4 years ago
- 中文到表情☆31Updated 3 years ago
- chinese real time voice cloning☆38Updated 5 years ago
- 一键将 Python 文件批量编译为 PYD/SO 文件! One-click batch compilation of Python files into PYD/SO files!☆32Updated 4 months ago
- ☆93Updated last year
- deecamp2019 51组 虚拟形象机器人☆33Updated 3 years ago
- 本项目是基于OpenCV的人脸识别技术，将一个完整的视频中自己想要了解的某个具体的人物片段，通过将视频分割成帧并且训练需要提取人物的面部特征，通过主成分分析算法进行人脸模型清洗并通过特征脸算法进行人脸识别，将该人物从视频中识别出来并将他的片段提取出来，组合成专属个人的视频剪…☆64Updated 4 years ago
- Recognize speech from an audio file and convert it into animation FBX☆23Updated 3 years ago
- 根据音乐节奏自动进行视频卡点剪辑☆17Updated 4 years ago
- 基于roop与codeFormer的换脸一体脚本☆20Updated 7 months ago
- 模拟剪映转换字幕☆41Updated 2 years ago
- 基于opencv+pyqt5开发的美颜化妆软件，功能包括：图像锐化、亮睛、红唇、瘦脸、美肤等☆72Updated 4 years ago
- 基于大模型的高质量情感虚拟人系统(Gradio+FUNASR+ChatGLM2-6B+GPT-SOVITS+EAT+GFPGAN)☆28Updated 3 months ago
- 人体动作捕捉与三维重建 SMPL 和 SMPLify 模型☆20Updated 4 years ago
- A website which shows examples of the various blendshapes that can be animated using ARKit.☆20Updated 3 years ago
- 基于rwkv.cpp项目制作webui，接入GPT-SoVITS朗读小说☆21Updated last year
- ☆33Updated 9 months ago
- 语音技术：文字转语音☆46Updated 2 years ago
- 使用 PaddleGAN 套件的 Wave2lip 模型给照片上的人“配音、配嘴型儿”~~☆26Updated 4 years ago
- 人像卡通化探索项目 (photo-to-cartoon translation project)☆63Updated 4 years ago
- 基于 NSFW Model 色情图片识别鉴黄 后面更新视频检测☆31Updated 3 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。☆21Updated last year
- 数字人开源项目 (Digital human project)☆156Updated 3 years ago
- 智能识别忘词、口误、静音片段的口播类剪辑助手，支持JianYing/Premiere/ShotCut/FCP格式导出。（An oral editing assistant that intelligently recognizes forgotten words, slip…☆20Updated 3 years ago
- 张艺谋(国师)一键声音克隆和恶搞文本生成项目☆17Updated 2 years ago
- 使用深度学习算法实现虚拟试衣镜，结合了人体姿态估计、人体分割、几何匹配和GAN，四种模型。仅仅只依赖opencv库就能运行☆267Updated 3 years ago