Symphomotion / README.md
nielsr's picture
nielsr HF Staff
Add model card and metadata for SymphoMotion
6d20081 verified
|
Raw
History Blame
2.08 kB
metadata
license: apache-2.0
pipeline_tag: image-to-video

SymphoMotion: Joint Control of Camera Motion and Object Dynamics for Coherent Video Generation

SymphoMotion is a unified motion-control framework that jointly governs camera trajectories and object dynamics within a single model. It features a Camera Trajectory Control mechanism that integrates explicit camera paths with geometry-aware cues, and an Object Dynamics Control mechanism that combines 2D visual guidance with 3D trajectory embeddings.

Project Website  arXiv  GitHub

Quick Start & Installation

To set up the environment and use these checkpoints, please refer to the instructions below or check out the Official Codebase.

git clone https://github.com/Grenoble-Zhang/SymphoMotion.git
cd SymphoMotion

# Create conda environment
conda create -n symphomotion python=3.10
conda activate symphomotion

# Install dependencies
pip install -r requirements.txt

Download Models

# Base model
huggingface-cli download Wan-AI/Wan2.1-I2V-14B-720P-Diffusers \
  --local-dir pretrained_models/Wan2.1-I2V-14B-720P-Diffusers

# SymphoMotion checkpoints
huggingface-cli download fateforward/Symphomotion \
  --include "pretrained_checkpoints/*" \
  --local-dir .

Citation

@article{zhang2026symphomotion,
  title={SymphoMotion: Joint Control of Camera Motion and Object Dynamics for Coherent Video Generation},
  author={Zhang, Guiyu and Chen, Yabo and Xiang, Xunzhi and Huang, Junchao and Wang, Zhongyu and Jiang, Li},
  journal={arXiv preprint arXiv:2604.03723},
  year={2026}
}