README.md

---
license: mit
---
# ControlTalk
Official code for "Controllable Talking Face Generation by Implicit Facial Keypoints Editing" 
[![Github](https://img.shields.io/badge/Github-8A2BE2)](https://github.com/NetEase-Media/ControlTalk)
[![python](https://img.shields.io/badge/Python-3.10-brightgreen)](https://github.com/NetEase-Media/ControlTalk)
[![arXiv](https://img.shields.io/badge/arXiv-2410.06885-b31b1b.svg?logo=arXiv)](https://arxiv.org/pdf/2406.02880)


## Code 

https://github.com/NetEase-Media/ControlTalk

## Inference

```bash
python inference.py \
        --source_video $source_video \
        --source_img_path  $source_image \
        --audio $audio \
        --save_as_video \
        --box -1 0 0 0 \
        # --img_mode  # if you only want to control the face expression
```