[](https://colab.research.google.com/github/Winfredy/SadTalker/blob/main/quick_demo.ipynb) [](https://huggingface.co/spaces/vinthony/SadTalker) [](https://colab.research.google.com/github/camenduru/stable-diffusion-webui-colab/blob/main/video/stable/stable_diffusion_1_5_video_webui_colab.ipynb) [](https://replicate.com/cjwbw/sadtalker)
Wenxuan Zhang *,1,2
Xiaodong Cun *,2
Xuan Wang 3
Yong Zhang 2
Xi Shen 2
Yu Guo1
Ying Shan 2
Fei Wang 1
1 Xi'an Jiaotong University 2 Tencent AI Lab 3 Ant Group
CVPR 2023
 TL;DR: single portrait image 🙎♂️ + audio 🎤 = talking head video 🎞.
- 🔥 Several new mode, eg, `still mode`, `reference mode`, `resize mode` are online for better and custom applications.
- 🔥 Happy to see more community demos at [bilibili](https://search.bilibili.com/all?keyword=sadtalker&from_source=webtop_search&spm_id_from=333.1007&search_source=3
), [Youtube](https://www.youtube.com/results?search_query=sadtalker&sp=CAM%253D) and [twitter #sadtalker](https://twitter.com/search?q=%23sadtalker&src=typed_query).
## 📋 Changelog (Previous changelog can be founded [here](docs/changlelog.md))
- __[2023.06.12]__: add more new features in WEBUI extension, see the discussion [here](https://github.com/OpenTalker/SadTalker/discussions/386).
- __[2023.06.05]__: release a new 512 beta face model. Fixed some bugs and improve the performance.
- __[2023.04.15]__: Adding automatic1111 colab by @camenduru, thanks for this awesome colab: [](https://colab.research.google.com/github/camenduru/stable-diffusion-webui-colab/blob/main/video/stable/stable_diffusion_1_5_video_webui_colab.ipynb).
- __[2023.04.12]__: adding a more detailed sd-webui installation document, fixed reinstallation problem.
- __[2023.04.12]__: Fixed the sd-webui safe issues becasue of the 3rd packages, optimize the output path in `sd-webui-extension`.
- __[2023.04.08]__: ❗️❗️❗️ In v0.0.2, we add a logo watermark to the generated video to prevent abusing since it is very realistic.
- __[2023.04.08]__: v0.0.2, full image animation, adding baidu driver for download checkpoints. Optimizing the logic about enhancer.
## 🚧 TODO: See the Discussion https://github.com/OpenTalker/SadTalker/issues/280
## If you have any problem, please view our [FAQ](docs/FAQ.md) before opening an issue.
## ⚙️ 1. Installation.
Tutorials from communities: [中文windows教程](https://www.bilibili.com/video/BV1Dc411W7V6/) | [日本語コース](https://br-d.fanbox.cc/posts/5685086?utm_campaign=manage_post_page&utm_medium=share&utm_source=twitter)
### Linux:
1. Installing [anaconda](https://www.anaconda.com/), python and git.
2. Creating the env and install the requirements.
```bash
git clone https://github.com/Winfredy/SadTalker.git
cd SadTalker
conda create -n sadtalker python=3.8
conda activate sadtalker
pip install torch==1.12.1+cu113 torchvision==0.13.1+cu113 torchaudio==0.12.1 --extra-index-url https://download.pytorch.org/whl/cu113
conda install ffmpeg
pip install -r requirements.txt
### tts is optional for gradio demo.
### pip install TTS
```
### Windows ([中文windows教程](https://www.bilibili.com/video/BV1Dc411W7V6/)):
1. Install [Python 3.10.6](https://www.python.org/downloads/windows/), checking "Add Python to PATH".
2. Install [git](https://git-scm.com/download/win) manually (OR `scoop install git` via [scoop](https://scoop.sh/)).
3. Install `ffmpeg`, following [this instruction](https://www.wikihow.com/Install-FFmpeg-on-Windows) (OR using `scoop install ffmpeg` via [scoop](https://scoop.sh/)).
4. Download our SadTalker repository, for example by running `git clone https://github.com/Winfredy/SadTalker.git`.
5. Download the `checkpoint` and `gfpgan` [below↓](https://github.com/Winfredy/SadTalker#-2-download-trained-models).
5. Run `start.bat` from Windows Explorer as normal, non-administrator, user, a gradio WebUI demo will be started.
### Macbook:
More tips about installnation on Macbook and the Docker file can be founded [here](docs/install.md)
## 📥 2. Download Trained Models.
You can run the following script to put all the models in the right place.
```bash
bash scripts/download_models.sh
```
Other alternatives:
> we also provide an offline patch (`gfpgan/`), thus, no model will be downloaded when generating.
**Google Driver**: download our pre-trained model from [ this link (main checkpoints)](https://drive.google.com/file/d/1gwWh45pF7aelNP_P78uDJL8Sycep-K7j/view?usp=sharing) and [ gfpgan (offline patch)](https://drive.google.com/file/d/19AIBsmfcHW6BRJmeqSFlG5fL445Xmsyi?usp=sharing)
**Github Release Page**: download all the files from the [lastest github release page](https://github.com/Winfredy/SadTalker/releases), and then, put it in ./checkpoints.
**百度云盘**: we provided the downloaded model in [checkpoints, 提取码: sadt.](https://pan.baidu.com/s/1P4fRgk9gaSutZnn8YW034Q?pwd=sadt) And [gfpgan, 提取码: sadt.](https://pan.baidu.com/s/1kb1BCPaLOWX1JJb9Czbn6w?pwd=sadt)
