| --- |
| license: apache-2.0 |
| library_name: diffusers |
| tags: |
| - computer-vision |
| - video-editing |
| - video-to-video |
| - diffusion |
| - flow-matching |
| - cvpr2026 |
| --- |
| |
| # [CVPR 2026] PropFly: Learning to Propagate via On-the-Fly Supervision from Pre-trained Video Diffusion Models |
|
|
| <div align="left"> |
| <a href="https://kaist-viclab.github.io/PropFly_site/"><img src="https://img.shields.io/badge/Project-Page-blue" alt="Project Page"></a> |
| <a href="https://arxiv.org/abs/2602.20583"><img src="https://img.shields.io/badge/arXiv-2602.20583-b31b1b.svg" alt="arXiv"></a> |
| <a href="https://github.com/pmjames16/PropFly"><img src="https://img.shields.io/badge/GitHub-Code-black?logo=github" alt="GitHub"></a> |
| </div> |
|
|
| Official model weights for **PropFly**. |
|
|
| PropFly is a novel training pipeline for propagation-based video editing that eliminates the need for large-scale, paired (source and edited) video datasets. Instead, it leverages on-the-fly supervision from pre-trained Video Diffusion Models (VDMs). |
|
|
|
|
| ## Model Description |
|
|
| Propagation-based video editing enables precise user control by propagating a single edited frame into subsequent frames while maintaining the original context. Our proposed method, **PropFly**, achieves this by: |
|
|
| 1. **On-the-Fly Supervision:** Utilizing a frozen pre-trained VDM to synthesize structurally aligned yet semantically distinct source (low-CFG) and target (high-CFG) latent pairs on the fly. |
| 2. **Guidance-Modulated Flow Matching (GMFM):** Training an adapter to learn propagation by predicting the VDM's high-CFG velocity, conditioned on the source video structure and the edited first frame style via GMFM loss. |
|
|
| This approach ensures temporally consistent and dynamic transformations, significantly outperforming state-of-the-art methods on various video editing tasks (evaluated on EditVerseBench and TGVE benchmarks). |
|
|
| ## Repository Structure |
|
|
| The model weights are stored in the `PropFly-1.3B/` directory. |
|
|
| ```text |
| ├── PropFly-1.3B/ |
| │ ├── diffusion_pytorch_model.bin # Model weights |
| ├── .gitattributes |
| └── README.md |
| ``` |
|
|
| ## Citation |
| ```text |
| @article{seo2026propfly, |
| title={PropFly: Learning to Propagate via On-the-Fly Supervision from Pre-trained Video Diffusion Models}, |
| author={Seo, Wonyong and Moon, Jaeho and Lee, Jaehyup and Kim, Soo Ye and Kim, Munchurl}, |
| journal={arXiv preprint arXiv:2602.20583}, |
| year={2026} |
| } |
| ``` |
