bb00d47a017e55ae0931434e76656edfcde2b9b8
📝 Changelog
MotionCtrl: A Unified and Flexible Motion Controller for Video Generation
🔥🔥 This is an official implement of MotionCtrl: A Unified and Flexible Motion Controller for Video Generation, which is capable of independently controlling the complex camera motion and object motion of the generated videos, with only a unified model. There are some results attained with MotionCtrl and more results are showcased in our Project Page.
⚙️ Environment
conda create -n motionctrl python=3.10.6
conda activate motionctrl
pip install -r requirements.txt
🏃 Inference
- Download the weights of MotionCtrl motionctrl.pth and put it to
./checkpoints. - Go into
configs/inference/run.shand setcondtypeas 'camera_motion', 'object_motion', or 'both'.
condtype=camera_motionmeans only control the camera motion in the generated video.condtype=object_motionmeans only control the object motion in the generated video.condtype=bothmeans control the camera motion and object motion in the generated video simultaneously.
-
Running scripts:
sh configs/inference/run.sh
📚 Citation
If you make use of our work, please cite our paper.
@inproceedings{wang2023motionctrl,
title={MotionCtrl: A Unified and Flexible Motion Controller for Video Generation},
author={Wang, Zhouxia and Yuan, Ziyang and Wang, Xintao and Chen, Tianshui and Xia, Menghan and Luo, Ping and Shan, Yin},
booktitle={arXiv preprint arXiv:2312.03641},
year={2023}
}
🤗 Acknowledgment
The current version of MotionCtrl is built on VideoCrafter. We appreciate the authors for sharing their awesome codebase.
❓ Contact
For any question, feel free to email wzhoux@connect.hku.hk or zhouzi1212@gmail.com.
Languages
Python
94.4%
JavaScript
2.8%
HTML
2.1%
CSS
0.4%
Shell
0.3%



