Awesome
<p align="center"> <img src="assets/logo.jpg" height=100> </p> <div align="center">MotionCtrl: A Unified and Flexible Motion Controller for Video Generation
[SIGGRAPH 2024 CONFERENCE PROCEEDINGS]
<div align="center">👉 MotionCtrl for <b><a href="https://github.com/TencentARC/MotionCtrl/tree/svd">[SVD]</a>, for <a href="https://github.com/TencentARC/MotionCtrl/tree/main">[VideoCrafter]</a>, for <a href="https://github.com/TencentARC/MotionCtrl/tree/animatediff">[AnimateDiff]</a></b></div>
</div>🔥🔥🔥 We have released both Training and Inference code of MotionCtrl deployed on AnimateDiff
🔥🔥 We release the codes, models and demos for MotionCtrl on Stable Video Diffusion (SVD).
https://github.com/TencentARC/MotionCtrl/assets/19488619/45d44bf5-d4bf-4e45-8628-2c8926b5954a
Official implementation of MotionCtrl: A Unified and Flexible Motion Controller for Video Generation.
MotionCtrl can Independently control complex camera motion and object motion of generated videos, with only a unified model.
Results of MotionCtrl+AnimateDiff
<div align="center"> <img src="assets/animatediff/sample-d971457c81bca597-Photon.gif", width="600"> <img src="assets/animatediff/sample-d971457c81bca597-HelloObject.gif", width="600"> <img src="assets/animatediff/sample-SPIN-LR-HelloObject.gif", width="600"> <img src="assets/animatediff/sample-none_motion-swaying_0.gif", width="600"> </div>Results of MotionCtrl+SVD
More results are in showcase_svd and our Project Page.
<div align="center"> <img src="assets/svd/00_ibzz5-dxv2h.gif", width="300"> <img src="assets/svd/01_5guvn-0x6v2.gif", width="300"> <img src="assets/svd/12_sn7bz-0hcaf.gif", width="300"> <img src="assets/svd/13_3lyco-4ru8j.gif", width="300"> </div>Results of MotionCtrl+VideoCrafter
More results are in our Project Page.
<div align="center"> <img src="assets/hpxvu-3d8ym.gif", width="600"> <img src="assets/w3nb7-9vz5t.gif", width="600"> <img src="assets/62n2a-wuvsw.gif", width="600"> <img src="assets/ilw96-ak827.gif", width="600"> </div>📝 Changelog
- 20231225: Release MotionCtrl deployed on LVDM/VideoCrafter.
- 20231225: Gradio demo available. 🤗
- 20231228: Provide local gradio demo for convenience.
- 20240115 More camera poses used for testing are provided in
dataset/camera_poses
- 20240115 Release MotionCtrl deployed on SVD. Codes are in the branch svd and Gradio Demo is available in 🤗 .
- ❗❗❗ Gradio demo of MotionCtrl deployed on VideoCrafter2 is available in 🤗 . You can also run it locally by
python -m app --share
.
- ❗❗❗ Release MotionCtrl deployed on AnimateDiff are available in branch animatediff, containing both training and inference code.
- 20240920 Provide scripts for collecting object trajectories with ParticleSfM.
- 20240920 We provide a HandyTrajDrawer to customize object trajectoires more conveniently.
⚙️ Environment
conda create -n motionctrl python=3.10.6
conda activate motionctrl
pip install -r requirements.txt
💫 Inference
-
Run local inference script
- Download the weights of MotionCtrl motionctrl.pth and put it to
./checkpoints
. - Go into
configs/inference/run.sh
and setcondtype
as 'camera_motion', 'object_motion', or 'both'.
condtype=camera_motion
means only control the camera motion in the generated video.condtype=object_motion
means only control the object motion in the generated video.condtype=both
means control the camera motion and object motion in the generated video simultaneously.
- Running scripts: sh configs/inference/run.sh
-
Run local gradio demo
python -m app --share
🔥🔥 Training 👉 Details
Preparing Dataset
-
- Following https://github.com/cashiwamochi/RealEstate10K_Downloader to download and process the videos.
- Corresponding Captions and List are provided in GoogleDrive.
-
WebVid with Object Trajectories
-
Preparing ParticleSfM. Our experiments is running on CentOS 8.5 and we provide a detailed install note in
dataset/object_trajectories/ParticleSfM_Install_Note.pdf
. -
Moving
dataset/object_trajectories/prepare_webvideo_len32.py
anddataset/object_trajectories/run_particlesfm_obj_traj.py
to ParticleSfM project. -
Step 1: Prepare sub-videos with lenth of 32 and size of 256 x 256.
## start_idx and end_idx is used to process a subset of the dataset in different machines parallelly python prepare_webvideo_len32.py --start_idx 0 --end_idx 1000
-
Step 2: Get object trajectories
root_dir="WebVid/train_256_32" start_idx=0 end_idx=1000 CUDA_VISIBLE_DEVICES=0 python run_particlesfm_obj_traj.py \ --root_dir $root_dir \ --start_idx $start_idx \ --end_idx $end_idx \
-
-
You can customize object Trajectories with our provided HandyTrajDrawer.
:books: Citation
If you make use of our work, please cite our paper.
@inproceedings{wang2024motionctrl,
title={Motionctrl: A unified and flexible motion controller for video generation},
author={Wang, Zhouxia and Yuan, Ziyang and Wang, Xintao and Li, Yaowei and Chen, Tianshui and Xia, Menghan and Luo, Ping and Shan, Ying},
booktitle={ACM SIGGRAPH 2024 Conference Papers},
pages={1--11},
year={2024}
}
🤗 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
.