github.com/TencentARC/MotionCtrl @main

MotionCtrl: A Unified and Flexible Motion Controller for Video Generation

[SIGGRAPH 2024 CONFERENCE PROCEEDINGS]

👉 MotionCtrl for [SVD], for [VideoCrafter], for [AnimateDiff]

   

🤗   🤗

---

🔥🔥🔥 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

<img src="https://github.com/TencentARC/MotionCtrl/raw/main/assets/animatediff/sample-d971457c81bca597-Photon.gif", width="600">
<img src="https://github.com/TencentARC/MotionCtrl/raw/main/assets/animatediff/sample-d971457c81bca597-HelloObject.gif", width="600">
<img src="https://github.com/TencentARC/MotionCtrl/raw/main/assets/animatediff/sample-SPIN-LR-HelloObject.gif", width="600">
<img src="https://github.com/TencentARC/MotionCtrl/raw/main/assets/animatediff/sample-none_motion-swaying_0.gif", width="600">

Results of MotionCtrl+SVD

More results are in showcase_svd and our Project Page.

<img src="https://github.com/TencentARC/MotionCtrl/raw/main/assets/svd/00_ibzz5-dxv2h.gif", width="300">
<img src="https://github.com/TencentARC/MotionCtrl/raw/main/assets/svd/01_5guvn-0x6v2.gif", width="300">
<img src="https://github.com/TencentARC/MotionCtrl/raw/main/assets/svd/12_sn7bz-0hcaf.gif", width="300">
<img src="https://github.com/TencentARC/MotionCtrl/raw/main/assets/svd/13_3lyco-4ru8j.gif", width="300">

Results of MotionCtrl+VideoCrafter

More results are in our Project Page.

<img src="https://github.com/TencentARC/MotionCtrl/raw/main/assets/hpxvu-3d8ym.gif", width="600">
<img src="https://github.com/TencentARC/MotionCtrl/raw/main/assets/w3nb7-9vz5t.gif", width="600">
<img src="https://github.com/TencentARC/MotionCtrl/raw/main/assets/62n2a-wuvsw.gif", width="600">
<img src="https://github.com/TencentARC/MotionCtrl/raw/main/assets/ilw96-ak827.gif", width="600">

---

📝 Changelog

• [x] 20231225: Release MotionCtrl deployed on LVDM/VideoCrafter.
• [x] 20231225: Gradio demo available. 🤗
• [x] 20231228: Provide local gradio demo for convenience.
• [x] 20240115 More camera poses used for testing are provided in dataset/camera_poses
• [x] 20240115 Release MotionCtrl deployed on SVD. Codes are in the branch svd and Gradio Demo is available in 🤗 .

• [x] ❗❗❗ Gradio demo of MotionCtrl deployed on VideoCrafter2 is available in 🤗 . You can also run it locally by python -m app --share.

• [x] ❗❗❗ Release MotionCtrl deployed on AnimateDiff are available in branch animatediff, containing both training and inference code.

• [x] 20240920 Provide scripts for collecting object trajectories with ParticleSfM.
• [x] 20240920 We provide a HandyTrajDrawer to customize object trajectories 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 set condtype 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

• RealEstate10K

  1. Following https://github.com/cashiwamochi/RealEstate10K_Downloader to download and process the videos.
  2. Corresponding Captions and List are provided in GoogleDrive.

• WebVid with Object Trajectories

  1. 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.
  2. Moving dataset/object_trajectories/prepare_webvideo_len32.py and dataset/object_trajectories/run_particlesfm_obj_traj.py to ParticleSfM project.

  3. 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 ``` 4. 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.