EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation
๐ EchoMimic Series
- EchoMimicV1: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditioning. GitHub
- EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation. GitHub
๐ฃ Updates
- [2025.01.03] ๐๐ฅ One Minute is All You Need to Generate Video. Accelerated EchoMimicV2 are released. The inference speed can be improved by 9x (from ~7mins/120frames to ~50s/120frames on A100 GPU).
- [2024.12.16] ๐ฅ RefImg-Pose Alignment Demo is now available, which involves aligning reference image, extracting pose from driving video, and generating video.
- [2024.11.27] ๐ฅ Installation tutorial is now available. Thanks AiMotionStudio for the contribution.
- [2024.11.22] ๐ฅ GradioUI is now available. Thanks @gluttony-10 for the contribution.
- [2024.11.22] ๐ฅ ComfyUI is now available. Thanks @smthemex for the contribution.
- [2024.11.21] ๐ฅ We release the EMTD dataset list and processing scripts.
- [2024.11.21] ๐ฅ We release our EchoMimicV2 codes and models.
- [2024.11.15] ๐ฅ Our paper is in public on arxiv.
๐ Gallery
Introduction
English Driven Audio
Chinese Driven Audio
โ๏ธ Automatic Installation
Download the Codes
git clone https://github.com/antgroup/echomimic_v2
cd echomimic_v2
Automatic Setup
- CUDA >= 11.7, Python == 3.10
sh linux_setup.sh
โ๏ธ Manual Installation
Download the Codes
git clone https://github.com/antgroup/echomimic_v2
cd echomimic_v2
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=3.10
conda activate echomimic
Install packages with pip
pip install pip -U
pip install torch==2.5.1 torchvision==0.20.1 torchaudio==2.5.1 xformers==0.0.28.post3 --index-url https://download.pytorch.org/whl/cu124
pip install torchao --index-url https://download.pytorch.org/whl/nightly/cu124
pip install -r requirements.txt
pip install --no-deps facenet_pytorch==2.6.0
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/EchoMimicV2 pretrained_weights
The pretrained_weights is organized as follows.
./pretrained_weights/
โโโ denoising_unet.pth
โโโ reference_unet.pth
โโโ motion_module.pth
โโโ pose_encoder.pth
โโโ sd-vae-ft-mse
โ โโโ ...
โโโ sd-image-variations-diffusers
โ โโโ ...
โโโ audio_processor
โโโ tiny.pt
In which denoising_unet.pth / reference_unet.pth / motion_module.pth / pose_encoder.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:
Inference on Demo
Run the gradio:
python app.py
Run the python inference script:
python infer.py --config='./configs/prompts/infer.yaml'
Run the python inference script for accelerated version. Make sure to check out the configuration for accelerated inference:
python infer_acc.py --config='./configs/prompts/infer_acc.yaml'
EMTD Dataset
Download dataset:
python ./EMTD_dataset/download.py
Slice dataset:
bash ./EMTD_dataset/slice.sh
Process dataset:
python ./EMTD_dataset/preprocess.py
Make sure to check out the discussions to learn how to start the inference.
๐ Release Plans
| Status | Milestone | ETA |
|---|---|---|
| โ | The inference source code of EchoMimicV2 meet everyone on GitHub | 21st Nov, 2024 |
| โ | Pretrained models trained on English and Mandarin Chinese on HuggingFace | 21st Nov, 2024 |
| โ | Pretrained models trained on English and Mandarin Chinese on ModelScope | 21st Nov, 2024 |
| โ | EMTD dataset list and processing scripts | 21st Nov, 2024 |
| โ | Jupyter demo with pose and reference image alignmnet | 16st Dec, 2024 |
| โ | Accelerated models | 3st Jan, 2025 |
| ๐ | Online Demo on ModelScope to be released | TBD |
| ๐ | Online Demo on HuggingFace to be released | TBD |
โ๏ธ Disclaimer
This project is intended for academic research, and we explicitly disclaim any responsibility for user-generated content. Users are solely liable for their actions while using the generative model. The project contributors have no legal affiliation with, nor accountability for, users' behaviors. It is imperative to use the generative model responsibly, adhering to both ethical and legal standards.
๐๐ป Acknowledgements
We would like to thank the contributors to the MimicMotion and Moore-AnimateAnyone repositories, for their open research and exploration.
We are also grateful to CyberHost and Vlogger for their outstanding work in the area of audio-driven human animation.
If we missed any open-source projects or related articles, we would like to complement the acknowledgement of this specific work immediately.
๐ Citation
If you find our work useful for your research, please consider citing the paper :
@misc{meng2024echomimicv2,
title={EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation},
author={Rang Meng, Xingyu Zhang, Yuming Li, Chenguang Ma},
year={2024},
eprint={2411.10061},
archivePrefix={arXiv}
}