LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control
1 Kuaishou Technology 2 University of Science and Technology of China 3 Fudan University
🔥 For more results, visit our homepage 🔥
## 🔥 Updates
- **`2024/07/10`**: 💪 We support audio and video concatenating, driving video auto-cropping, and template making to protect privacy. More to see [here](assets/docs/changelog/2024-07-10.md).
- **`2024/07/09`**: 🤗 We released the [HuggingFace Space](https://huggingface.co/spaces/KwaiVGI/liveportrait), thanks to the HF team and [Gradio](https://github.com/gradio-app/gradio)!
- **`2024/07/04`**: 😊 We released the initial version of the inference code and models. Continuous updates, stay tuned!
- **`2024/07/04`**: 🔥 We released the [homepage](https://liveportrait.github.io) and technical report on [arXiv](https://arxiv.org/pdf/2407.03168).
## Introduction
This repo, named **LivePortrait**, contains the official PyTorch implementation of our paper [LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control](https://arxiv.org/pdf/2407.03168).
We are actively updating and improving this repository. If you find any bugs or have suggestions, welcome to raise issues or submit pull requests (PR) 💖.
## 🔥 Getting Started
### 1. Clone the code and prepare the environment
```bash
git clone https://github.com/KwaiVGI/LivePortrait
cd LivePortrait
# create env using conda
conda create -n LivePortrait python==3.9.18
conda activate LivePortrait
# install dependencies with pip
pip install -r requirements.txt
```
**Note:** make sure your system has [FFmpeg](https://ffmpeg.org/) installed!
### 2. Download pretrained weights
The easiest way to download the pretrained weights is from HuggingFace:
```bash
# you may need to run `git lfs install` first
git clone https://huggingface.co/KwaiVGI/liveportrait pretrained_weights
```
Alternatively, you can download all pretrained weights from [Google Drive](https://drive.google.com/drive/folders/1UtKgzKjFAOmZkhNK-OYT0caJ_w2XAnib) or [Baidu Yun](https://pan.baidu.com/s/1MGctWmNla_vZxDbEp2Dtzw?pwd=z5cn). Unzip and place them in `./pretrained_weights`.
Ensuring the directory structure is as follows, or contains:
```text
pretrained_weights
├── insightface
│ └── models
│ └── buffalo_l
│ ├── 2d106det.onnx
│ └── det_10g.onnx
└── liveportrait
├── base_models
│ ├── appearance_feature_extractor.pth
│ ├── motion_extractor.pth
│ ├── spade_generator.pth
│ └── warping_module.pth
├── landmark.onnx
└── retargeting_models
└── stitching_retargeting_module.pth
```
### 3. Inference 🚀
#### Fast hands-on
```bash
python inference.py
```
If the script runs successfully, you will get an output mp4 file named `animations/s6--d0_concat.mp4`. This file includes the following results: driving video, input image, and generated result.
Or, you can change the input by specifying the `-s` and `-d` arguments:
```bash
python inference.py -s assets/examples/source/s9.jpg -d assets/examples/driving/d0.mp4
# disable pasting back to run faster
python inference.py -s assets/examples/source/s9.jpg -d assets/examples/driving/d0.mp4 --no_flag_pasteback
# more options to see
python inference.py -h
```
#### Driving video auto-cropping
📕 To use your own driving video, we **recommend**:
- Crop it to a **1:1** aspect ratio (e.g., 512x512 or 256x256 pixels), or enable auto-cropping by `--flag_crop_driving_video`.
- Focus on the head area, similar to the example videos.
- Minimize shoulder movement.
- Make sure the first frame of driving video is a frontal face with **neutral expression**.
Below is a auto-cropping case by `--flag_crop_driving_video`:
```bash
python inference.py -s assets/examples/source/s9.jpg -d assets/examples/driving/d13.mp4 --flag_crop_driving_video
```
If you find the results of auto-cropping is not well, you can modify the `--scale_crop_video`, `--vy_ratio_crop_video` options to adjust the scale and offset, or do it manually.
#### Motion template making
You can also use the auto-generated motion template files ending with `.pkl` to speed up inference, and **protect privacy**, such as:
```bash
python inference.py -s assets/examples/source/s9.jpg -d assets/examples/driving/d5.pkl
```
**Discover more interesting results on our [Homepage](https://liveportrait.github.io)** 😊
### 4. Gradio interface 🤗
We also provide a Gradio interface for a better experience, just run by:
```bash
python app.py
```
You can specify the `--server_port`, `--share`, `--server_name` arguments to satisfy your needs!
**Or, try it out effortlessly on [HuggingFace](https://huggingface.co/spaces/KwaiVGI/LivePortrait) 🤗**
### 5. Inference speed evaluation 🚀🚀🚀
We have also provided a script to evaluate the inference speed of each module:
```bash
python speed.py
```
Below are the results of inferring one frame on an RTX 4090 GPU using the native PyTorch framework with `torch.compile`:
| Model | Parameters(M) | Model Size(MB) | Inference(ms) |
|-----------------------------------|:-------------:|:--------------:|:-------------:|
| Appearance Feature Extractor | 0.84 | 3.3 | 0.82 |
| Motion Extractor | 28.12 | 108 | 0.84 |
| Spade Generator | 55.37 | 212 | 7.59 |
| Warping Module | 45.53 | 174 | 5.21 |
| Stitching and Retargeting Modules | 0.23 | 2.3 | 0.31 |
*Note: The values for the Stitching and Retargeting Modules represent the combined parameter counts and total inference time of three sequential MLP networks.*
## Community Resources 🤗
Discover the invaluable resources contributed by our community to enhance your LivePortrait experience:
- [ComfyUI-LivePortraitKJ](https://github.com/kijai/ComfyUI-LivePortraitKJ) by [@kijai](https://github.com/kijai)
- [comfyui-liveportrait](https://github.com/shadowcz007/comfyui-liveportrait) by [@shadowcz007](https://github.com/shadowcz007)
- [LivePortrait hands-on tutorial](https://www.youtube.com/watch?v=uyjSTAOY7yI) by [@AI Search](https://www.youtube.com/@theAIsearch)
- [ComfyUI tutorial](https://www.youtube.com/watch?v=8-IcDDmiUMM) by [@Sebastian Kamph](https://www.youtube.com/@sebastiankamph)
- [LivePortrait In ComfyUI](https://www.youtube.com/watch?v=aFcS31OWMjE) by [@Benji](https://www.youtube.com/@TheFutureThinker)
- [Replicate Playground](https://replicate.com/fofr/live-portrait) and [cog-comfyui](https://github.com/fofr/cog-comfyui) by [@fofr](https://github.com/fofr)
And many more amazing contributions from our community!
## Acknowledgements
We would like to thank the contributors of [FOMM](https://github.com/AliaksandrSiarohin/first-order-model), [Open Facevid2vid](https://github.com/zhanglonghao1992/One-Shot_Free-View_Neural_Talking_Head_Synthesis), [SPADE](https://github.com/NVlabs/SPADE), [InsightFace](https://github.com/deepinsight/insightface) repositories, for their open research and contributions.
## Citation 💖
If you find LivePortrait useful for your research, welcome to 🌟 this repo and cite our work using the following BibTeX:
```bibtex
@article{guo2024liveportrait,
title = {LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control},
author = {Guo, Jianzhu and Zhang, Dingyun and Liu, Xiaoqiang and Zhong, Zhizhou and Zhang, Yuan and Wan, Pengfei and Zhang, Di},
journal = {arXiv preprint arXiv:2407.03168},
year = {2024}
}
```
