hyfevian / wav2lip384Links
wav2lip384生成器网格权重——来自不蠢不蠢
☆116Updated 4 months ago
Alternatives and similar repositories for wav2lip384
Users that are interested in wav2lip384 are comparing it to the libraries listed below
Sorting:
- A docker free offline version for HeyGem; Python and Linux is all you need!☆296Updated 2 months ago
- ☆72Updated last week
- ☆231Updated last year
- ☆325Updated last month
- The fastest digital human algorithm, now on your desktop.☆539Updated last month
- JoyHallo: Digital human model for Mandarin☆503Updated 8 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☆76Updated 7 months ago
- Real time streaming talking head☆480Updated last year
- ☆43Updated last week
- ☆41Updated last year
- 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
- Simple and fast wav2lip using new 256x256 resolution trained onnx-converted model for inference. Easy installation☆42Updated 9 months ago
- Full version of wav2lip-onnx including face alignment and face enhancement and more...☆131Updated last month
- 开源的LstmSync数字人泛化模型,只做最好的泛化模型!☆51Updated 2 weeks ago
- ☆198Updated 2 years ago
- ☆269Updated last year
- python库,实现推送实时rtmp音视频流☆127Updated last year
- 基于MuseTalk的数字人代码。☆30Updated 10 months ago
- ☆36Updated last year
- DICE-Talk is a diffusion-based emotional talking head generation method that can generate vivid and diverse emotions for speaking portrai…☆230Updated 2 months ago
- Project Page repo of OmniTalker: Real-Time Text-Driven Talking Head Generation with In-Context Audio-Visual Style Replication☆369Updated 3 months ago
- ☆591Updated last week
- 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
- 在DH_live项目基础上修改,添加webui界面☆64Updated 3 months ago
- Colab for making Wav2Lip high quality and easy to use☆825Updated last year
- talking-face video editing☆371Updated 5 months ago
- ☆75Updated 9 months ago
- 实时互动的GPT数字人技术笔记,不是数字人开源项目☆483Updated last month
- ☆630Updated 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