MimicMotion

MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance
Yuang Zhang^1,2, Jiaxi Gu¹, Li-Wen Wang¹, Han Wang^1,2, Junqi Cheng¹, Yuefeng Zhu¹, Fangyuan Zou¹
[¹Tencent; ²Shanghai Jiao Tong University]

Highlights: rich details, good temporal smoothness, and long video length.

Overview

An overview of the framework of MimicMotion.

In recent years, generative artificial intelligence has achieved significant advancements in the field of image generation, spawning a variety of applications. However, video generation still faces considerable challenges in various aspects such as controllability, video length, and richness of details, which hinder the application and popularization of this technology. In this work, we propose a controllable video generation framework, dubbed MimicMotion, which can generate high-quality videos of arbitrary length with any motion guidance. Comparing with previous methods, our approach has several highlights. Firstly, with confidence-aware pose guidance, temporal smoothness can be achieved so model robustness can be enhanced with large-scale training data. Secondly, regional loss amplification based on pose confidence significantly eases the distortion of image significantly. Lastly, for generating long smooth videos, a progressive latent fusion strategy is proposed. By this means, videos of arbitrary length can be generated with acceptable resource consumption. With extensive experiments and user studies, MimicMotion demonstrates significant improvements over previous approaches in multiple aspects.

Quickstart

Environment setup

Recommend python 3+ with torch 2.x are validated with an Nvidia V100 GPU. Follow the command below to install all the dependencies of python:

conda env create -f environment.yaml
conda activate mimicmotion

Download weights

Please download weights manually as follows:

cd MimicMotions/
mkdir models

1. Download SVD model: stabilityai/stable-video-diffusion-img2vid-xt-1-1

   git lfs install
   git clone https://huggingface.co/stabilityai/stable-video-diffusion-img2vid-xt-1-1
   mkdir -p models/SVD
   mv stable-video-diffusion-img2vid-xt-1-1 models/SVD/
   

2. Download DWPose pretrained model: dwpose

   git lfs install
   git clone https://huggingface.co/yzd-v/DWPose
   mv DWPose models/
   

3. Download the pre-trained checkpoint of MimicMotion from Huggingface

   curl -o models/MimicMotion.pth https://huggingface.co/ixaac/MimicMotion/resolve/main/MimicMotion.pth
   

Finally, all the weights should be organized in models as follows

models/
├── DWPose
│   ├── dw-ll_ucoco_384.onnx
│   └── yolox_l.onnx
├── SVD
│   └──stable-video-diffusion-img2vid-xt-1-1
└── MimicMotion.pth

Model inference

We provide the inference script.

python inference.py --inference_config configs/test.yaml

Citation

@article{mimicmotion2024,
  title={MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance},
  author={Yuang Zhang and Jiaxi Gu and Li-Wen Wang and Han Wang and Junqi Cheng and Yuefeng Zhu and Fangyuan Zou},
  journal={arXiv preprint arXiv:2406.19680},
  year={2024}
}