justld / dofaker
An easy use face swap tool for images and tools only depend on onnxruntime.
☆75Updated last year
Alternatives and similar repositories for dofaker:
Users that are interested in dofaker are comparing it to the libraries listed below
- Простое WebUI на Flask для EasyWav2Lip☆26Updated last year
- ☆50Updated 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 last year
- FaceChain is a deep-learning toolchain for generating your Digital-Twin.☆47Updated last year
- Windows不用搭建环境，解压即用！☆25Updated last year
- Windows不用搭建环境只要英伟达显卡就行，解压即用！☆41Updated 9 months ago
- make your Speaker talking as Native style with own voice！☆251Updated last year
- 基于roop与codeFormer的换脸一体脚本☆20Updated last month
- 在DH_live项目基础上修改，添加webui界面☆60Updated 2 weeks 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
- 基于大模型的高质 量情感虚拟人系统(Gradio+FUNASR+ChatGLM2-6B+GPT-SOVITS+EAT+GFPGAN)☆26Updated 8 months ago
- 使用onnxruntime部署facefusion换脸，包含C++和Python两个版本的程序☆110Updated last year
- ☆41Updated last year
- 全网首发AI人物写真、 AI数字分身、AI头像、Lora、comfyui、stable diffusion、SD、instant ID、提供类妙鸭相机小程序代部署，源码部署，facechain、ip-adapter、AI写真系统，当前AI写真市场火爆，本项目只仅需1张照片即…☆31Updated 11 months ago
- Chinese Stable Diffusion, zh SD,中文文生图，中文SD，中文Stable Diffusion☆48Updated 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！☆23Updated last year
- Simple and fast wav2lip using new 256x256 resolution trained onnx-converted model for inference. Easy installation☆40Updated 6 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☆103Updated 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☆70Updated 4 months ago
- Just a suturing monster project.☆40Updated last year
- wav2lip384生成器网格权重——来自不蠢不蠢☆89Updated 2 months ago
- ☆35Updated last year
- ☆21Updated last year
- ☆75Updated 6 months ago
- 跨语种语音克隆,中文版Webui☆51Updated last year
- ☆46Updated last year
- ☆52Updated last year
- 基于DCT-Net的图片/视频转绘gradio界面webui☆26Updated 10 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…☆52Updated last year
- 使用GFPGAN进行视频修复☆20Updated 2 years ago