circle-rotate-lora

<p align="center"> <h1 align="center">Circle-Rotate LoRA</h1> <h3 align="center">Implicit Motion Alignment for Rigid-Body Video Generation</h3> </p> <p align="center"> <a href="https://github.com/Jklaity/Circle-Rotate"> <img src='https://img.shields.io/badge/GitHub-Code-black?style=flat&logo=github' alt='GitHub'> </a> <a href="https://huggingface.co/datasets/jk1741391802/circle-rotate-dataset"> <img src='https://img.shields.io/badge/HuggingFace-Dataset-yellow?style=flat&logo=huggingface' alt='Dataset'> </a> <a href="https://arxiv.org/abs/xxxx.xxxxx"> <img src='https://img.shields.io/badge/arXiv-Paper-red?style=flat&logo=arxiv' alt='arXiv'> </a> </p> <p align="center"> <img src="https://raw.githubusercontent.com/Jklaity/Circle-Rotate/main/assets/teaser.gif" width="100%"> </p>

Overview

Circle-Rotate LoRA enables smooth circular camera motion around static subjects in image-to-video generation. Fine-tuned on the Wan2.2 I2V model with only 1.4% parameter overhead, it achieves 15.1% subject drift reduction compared to baselines.

Key Features

• Stable Subject: Objects remain stationary while camera orbits smoothly
• Data-Centric: No explicit 3D pose supervision required
• Lightweight: Only 1.4% LoRA parameters (high/low noise each 0.7%)
• Plug & Play: Works with ComfyUI and standard inference pipelines

Demo Results

<table> <tr> <td align="center"><b>Baseline</b></td> <td align="center"><b>Ours</b></td> </tr> <tr> <td align="center"><img src="https://raw.githubusercontent.com/Jklaity/Circle-Rotate/main/assets/demo1_base.gif" width="280"></td> <td align="center"><img src="https://raw.githubusercontent.com/Jklaity/Circle-Rotate/main/assets/demo1_ours.gif" width="280"></td> </tr> <tr> <td align="center"><img src="https://raw.githubusercontent.com/Jklaity/Circle-Rotate/main/assets/cat_others.gif" width="280"></td> <td align="center"><img src="https://raw.githubusercontent.com/Jklaity/Circle-Rotate/main/assets/cat_ours.gif" width="280"></td> </tr> <tr> <td align="center"><img src="https://raw.githubusercontent.com/Jklaity/Circle-Rotate/main/assets/person_others.gif" width="280"></td> <td align="center"><img src="https://raw.githubusercontent.com/Jklaity/Circle-Rotate/main/assets/person_ours.gif" width="280"></td> </tr> </table>

Model Files

Both files are required for optimal results.

Usage

With ComfyUI

1. Download both LoRA files to ComfyUI/models/loras/
2. Load workflow.json from the GitHub repo
3. Run inference

Command Line

# Clone the repository
git clone https://github.com/Jklaity/Circle-Rotate.git
cd Circle-Rotate

# Download LoRA weights
huggingface-cli download jk1741391802/circle-rotate-lora --local-dir ./checkpoints

# Run inference
python inference.py \
    --first_frame examples/first.png \
    --last_frame examples/last.png \
    --prompt "A car, camera smoothly orbits left" \
    --output output.mp4

Recommended Parameters

Citation

@article{circle-rotate2025,
  title={Implicit Motion Alignment: A Data-Centric Empirical Study for Rigid-Body Video Generation},
  year={2025}
}

License

Apache License 2.0