Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
GeneFace++: Generalized and Stable Real-Time 3D Talking Face Generation; Official Code
| Date | Stars |
|---|---|
| 2026-07-24 | 1808 |
| 2026-07-25 | 1808 |
| 2026-07-28 | 1808 |
| 2026-07-30 | 1808 |
| 2026-08-06 | 1808 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# GeneFace++: Generalized and Stable Real-Time 3D Talking Face Generation
[](https://arxiv.org/abs/2305.00787)| [](https://github.com/yerfor/GeneFacePlusPlus) | [中文文档](./README-zh.md)
This is the official implementation of GeneFace++ [Paper](https://arxiv.org/abs/2301.13430) with Pytorch, which enables high lip-sync, high video-reality and high system-efficiency 3D talking face generation. You can visit our [Demo Page](https://genefaceplusplus.github.io/) to watch demo videos and learn more details.
<p align="center">
<br>
<img src="assets/geneface++.png" width="100%"/>
<br>
</p>
# 🔥MimicTalk Released
**We have released the code of MimicTalk ([https://github.com/yerfor/MimicTalk/](https://github.com/yerfor/MimicTalk/)), which is a SOTA NeRF-based person-specific talking face method and achieves better visual quality and enables talking style control.**
## You may also interested in
- We release Real3D-portrait (ICLR 2024 Spotlight), ([https://github.com/yerfor/Real3DPortrait](https://github.com/yerfor/Real3DPortrait)), a NeRF-based one-shot talking face system. Only upload one image and enjoy realistic talking face!
## Quick Start!
We provide a guide for a quick start in GeneFace++.
- Step 1: Follow the steps in `docs/prepare_env/install_guide.md`, create a new python environment named `geneface`, and download 3DMM files into `deep_3drecib/BFM`.
- Step 2: Download pre-processed dataset of May([Google Drive](https://drive.google.com/drive/folders/1SwZ7uRa5ESzzq_Cd21-Lk5heAZxa9oZO?usp=sharing) or [BaiduYun Disk](https://pan.baidu.com/s/1U_FalVoxgb9sAb9FD1cZEw?pwd=98n4) with password 98n4), and place it here `data/binary/videos/May/trainval_dataset.npy`
- Step 3: Download pre-trained audio-to-motino model `audio2motion_vae.zip` ([Google Drive](https://drive.google.com/drive/folders/1M6CQH52lG_yZj7oCMaepn3Qsvb-8W2pT?usp=sharing) or [BaiduYun Disk](https://pan.baidu.com/s/19UZxMrO-ZvkOeYzUkOKsTQ?pwd=9cqp) with password 9cqp) and motion-to-video checkpoint `motion2video_nerf.zip`, which is specific to May (in this [Google Drive](https://drive.google.com/drive/folders/1M6CQH52lG_yZj7oCMaepn3Qsvb-8W2pT?usp=sharing) or in this[BaiduYun Disk](https://pan.baidu.com/s/1U_FalVoxgb9sAb9FD1cZEw?pwd=98n4) with password 98n4), and unzip them to `./checkpoints/`
After these steps，your directories `checkpoints` and `data` should be like this：
```
> checkpoints
> audio2motion_vae
> motion2video_nerf
> may_head
> may_torso
> data
> binary
> videos
> May
trainval_dataset.npy
```
- Step 4: activate `geneface` Python environment, and execute:
```bash
export PYTHONPATH=./
python inference/genefacepp_infer.py --a2m_ckpt=checkpoints/audio2motion_vae --head_ckpt= --torso_ckpt=checkpoints/motion2video_nerf/may_torso --drv_aud=data/raw/val_wavs/MacronSpeech.wav --out_name=may_demo.mp4
```
Or you can play with our Gradio WebUI:
```bash
export PYTHONPATH=./
python inference/app_genefacepp.py --a2m_ckpt=checkpoints/audio2motion_vae --head_ckpt= --torso_ckpt=checkpoints/motion2video_nerf/may_torso
```
Or use our provided [Google Colab](https://colab.research.google.com/github/yerfor/GeneFacePlusPlus/blob/main/inference/genefacepp_demo.ipynb) and run all cells in it.
## Train GeneFace++ with your own videos
Please refer to details in `docs/process_data` and `docs/train_and_infer`.
Below are answers to frequently asked questions when training GeneFace++ on custom videos:
- Please make sure that the head segment occupies a relatively large region in the video (e.g., similar to the provided `May.mp4`). Or you need to hand-crop your training video. [issue](https://github.com/yerfor/GeneFacePlusPlus/issues/30)
- Make sure that the talking person appears in every frame of the video, otherwise the data preprocessing pipeline may be failExcerpt of 5,225 characters
Read on GitHub
Zhenhui Ye · Zhejiang University
10
1
1
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:f3055d5c10e21871, topic:nerf