---
title: EchoMimic
emoji: π¨
colorFrom: pink
colorTo: blue
sdk: gradio
sdk_version: 5.4.0
app_file: webgui.py
pinned: false
suggested_hardware: a10g-large
---
EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditioning
*Equal Contribution.
Terminal Technology Department, Alipay, Ant Group.
## 📣 📣 Updates
* [2024.07.17] π₯π₯π₯ Accelerated models and pipe are released. The inference speed can be improved by **10x** (from ~7mins/240frames to ~50s/240frames on V100 GPU)
* [2024.07.14] π₯ [ComfyUI](https://github.com/smthemex/ComfyUI_EchoMimic) is now available. Thanks @smthemex for the contribution.
* [2024.07.13] π₯ Thanks [NewGenAI](https://www.youtube.com/@StableAIHub) for the [video installation tutorial](https://www.youtube.com/watch?v=8R0lTIY7tfI).
* [2024.07.13] π₯ We release our pose&audio driven codes and models.
* [2024.07.12] π₯ WebUI and GradioUI versions are released. We thank @greengerong @Robin021 and @O-O1024 for their contributions.
* [2024.07.12] π₯ Our [paper](https://arxiv.org/abs/2407.08136) is in public on arxiv.
* [2024.07.09] π₯ We release our audio driven codes and models.
## Gallery
### Audio Driven (Sing)
### Audio Driven (English)
### Audio Driven (Chinese)
### Landmark Driven
### Audio + Selected Landmark Driven
**οΌSome demo images above are sourced from image websites. If there is any infringement, we will immediately remove them and apologize.οΌ**
## Installation
### Download the Codes
```bash
git clone https://github.com/BadToBest/EchoMimic
cd EchoMimic
```
### Python Environment Setup
- Tested System Environment: Centos 7.2/Ubuntu 22.04, Cuda >= 11.7
- Tested GPUs: A100(80G) / RTX4090D (24G) / V100(16G)
- Tested Python Version: 3.8 / 3.10 / 3.11
Create conda environment (Recommended):
```bash
conda create -n echomimic python=3.8
conda activate echomimic
```
Install packages with `pip`
```bash
pip install -r requirements.txt
```
### Download ffmpeg-static
Download and decompress [ffmpeg-static](https://www.johnvansickle.com/ffmpeg/old-releases/ffmpeg-4.4-amd64-static.tar.xz), then
```
export FFMPEG_PATH=/path/to/ffmpeg-4.4-amd64-static
```
### Download pretrained weights
```shell
git lfs install
git clone https://huggingface.co/BadToBest/EchoMimic pretrained_weights
```
The **pretrained_weights** is organized as follows.
```
./pretrained_weights/
βββ denoising_unet.pth
βββ reference_unet.pth
βββ motion_module.pth
βββ face_locator.pth
βββ sd-vae-ft-mse
β βββ ...
βββ sd-image-variations-diffusers
β βββ ...
βββ audio_processor
βββ whisper_tiny.pt
```
In which **denoising_unet.pth** / **reference_unet.pth** / **motion_module.pth** / **face_locator.pth** are the main checkpoints of **EchoMimic**. Other models in this hub can be also downloaded from it's original hub, thanks to their brilliant works:
- [sd-vae-ft-mse](https://huggingface.co/stabilityai/sd-vae-ft-mse)
- [sd-image-variations-diffusers](https://huggingface.co/lambdalabs/sd-image-variations-diffusers)
- [audio_processor(whisper)](https://openaipublic.azureedge.net/main/whisper/models/65147644a518d12f04e32d6f3b26facc3f8dd46e5390956a9424a650c0ce22b9/tiny.pt)
### Audio-Drived Algo Inference
Run the python inference script:
```bash
python -u infer_audio2vid.py
python -u infer_audio2vid_pose.py
```
### Audio-Drived Algo Inference On Your Own Cases
Edit the inference config file **./configs/prompts/animation.yaml**, and add your own case:
```bash
test_cases:
"path/to/your/image":
- "path/to/your/audio"
```
The run the python inference script:
```bash
python -u infer_audio2vid.py
```
### Motion Alignment between Ref. Img. and Driven Vid.
(Firstly download the checkpoints with '_pose.pth' postfix from huggingface)
Edit driver_video and ref_image to your path in demo_motion_sync.py, then run
```bash
python -u demo_motion_sync.py
```
### Audio&Pose-Drived Algo Inference
Edit ./configs/prompts/animation_pose.yaml, then run
```bash
python -u infer_audio2vid_pose.py
```
### Pose-Drived Algo Inference
Set draw_mouse=True in line 135 of infer_audio2vid_pose.py. Edit ./configs/prompts/animation_pose.yaml, then run
```bash
python -u infer_audio2vid_pose.py
```
### Run the Gradio UI
Thanks to the contribution from @Robin021:
```bash
python -u webgui.py --server_port=3000
```
## Release Plans
| Status | Milestone | ETA |
|:--------:|:-------------------------------------------------------------------------|:--:|
| β
| The inference source code of the Audio-Driven algo meet everyone on GitHub | 9th July, 2024 |
| β
| Pretrained models trained on English and Mandarin Chinese to be released | 9th July, 2024 |
| β
| The inference source code of the Pose-Driven algo meet everyone on GitHub | 13th July, 2024 |
| β
| Pretrained models with better pose control to be released | 13th July, 2024 |
| β
| Accelerated models to be released | 17th July, 2024 |
| π | Pretrained models with better sing performance to be released | TBD |
| π | Large-Scale and High-resolution Chinese-Based Talking Head Dataset | TBD |
## Acknowledgements
We would like to thank the contributors to the [AnimateDiff](https://github.com/guoyww/AnimateDiff), [Moore-AnimateAnyone](https://github.com/MooreThreads/Moore-AnimateAnyone) and [MuseTalk](https://github.com/TMElyralab/MuseTalk) repositories, for their open research and exploration.
We are also grateful to [V-Express](https://github.com/tencent-ailab/V-Express) and [hallo](https://github.com/fudan-generative-vision/hallo) for their outstanding work in the area of diffusion-based talking heads.
If we missed any open-source projects or related articles, we would like to complement the acknowledgement of this specific work immediately.
## Citation
If you find our work useful for your research, please consider citing the paper :
```
@misc{chen2024echomimic,
title={EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditioning},
author={Zhiyuan Chen, Jiajiong Cao, Zhiquan Chen, Yuming Li, Chenguang Ma},
year={2024},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
```
## Star History
[![Star History Chart](https://api.star-history.com/svg?repos=BadToBest/EchoMimic&type=Date)](https://star-history.com/?spm=5176.28103460.0.0.342a3da23STWrU#BadToBest/EchoMimic&Date)