/EchoMimic

Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditioning

Primary LanguagePythonApache License 2.0Apache-2.0

EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditioning

Zhiyuan Chen*Jiajiong Cao*Zhiquan ChenYuming LiChenguang Ma
*Equal Contribution.
Terminal Technology Department, Alipay, Ant Group.

Gallery

Audio Driven (Sing)

s_01.mp4
s_02.mp4
s_03.mp4

Audio Driven (English)

en_01.mp4
en_03.mp4
en_05.mp4

Audio Driven (Chinese)

ch_02.mp4
ch_03.mp4
ch_04.mp4

Landmark Driven

po_01.mp4
po_02.mp4
po_03.mp4

Audio + Selected Landmark Driven

ap_04.mp4
ap_05.mp4
ap_06.mp4

(Some demo images above are sourced from image websites. If there is any infringement, we will immediately remove them and apologize.)

Installation

Download the Codes

  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):

  conda create -n echomimic python=3.8
  conda activate echomimic

Install packages with pip

  pip install -r requirements.txt

Download ffmpeg-static

Download and decompress ffmpeg-static, then

export FFMPEG_PATH=/path/to/ffmpeg-4.4-amd64-static

Download pretrained weights

git lfs install
git clone https://huggingface.co/BadToBest/EchoMimic pretrained_weights

The pretrained_weights is organized as follows.

./pretrained_weights/
├── denoising_unet.pth
├── reference_unet.pth
├── motion_module.pth
├── face_locator.pth
├── sd-vae-ft-mse
│   └── ...
├── sd-image-variations-diffusers
│   └── ...
└── audio_processor
    └── 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:

Audio-Drived Algo Inference

Run the python inference script:

  python -u infer_audio2vid.py

Audio-Drived Algo Inference On Your Own Cases

Edit the inference config file ./configs/prompts/animation.yaml, and add your own case:

test_cases:
  "path/to/your/image":
    - "path/to/your/audio"

The run the python inference script:

  python -u infer_audio2vid.py

Release Plans

Status Milestone ETA
The inference source code of the Audio-Driven algo meet everyone on GitHub 9th July, 2024
Pretrained models trained on English and Mandarin Chinese to be released 9th July, 2024
🚀 The inference source code of the Pose-Driven algo meet everyone on GitHub 13th July, 2024
🚀 Pretrained models with better pose control to be released 13th July, 2024
🚀 Pretrained models with better sing performance to be released TBD
🚀 Accelerated models to be released TBD
🚀 Large-Scale and High-resolution Chinese-Based Talking Head Dataset TBD

Acknowledgements

We would like to thank the contributors to the AnimateDiff, Moore-AnimateAnyone and MuseTalk repositories, for their open research and exploration.

We are also grateful to V-Express and 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.

EchoMimic Communities

There are numerous developers actively engaged in projects centered around EchoMimic, and we are compelled to express our profound gratitude for their invaluable contributions. In acknowledgment of their efforts, we are pleased to highlight a selection of exemplary repositories below. These repositories have significantly augmented the capabilities of EchoMimic, thereby enhancing its potency and versatility in application.

WebUi version: https://github.com/greengerong/EchoMimic

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}
}