--- 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

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} } ```