ViFeEdit: A Video-Free Tuner of Your Video Diffusion Transformer
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915867278704640 |
|---|---|
| author | Yu, Ruonan Tan, Zhenxiong Chen, Zigeng Liu, Songhua Wang, Xinchao |
| author_facet | Yu, Ruonan Tan, Zhenxiong Chen, Zigeng Liu, Songhua Wang, Xinchao |
| contents | Diffusion Transformers (DiTs) have demonstrated remarkable scalability and quality in image and video generation, prompting growing interest in extending them to controllable generation and editing tasks. However, compared to the image counterparts, progress in video control and editing remains limited, mainly due to the scarcity of paired video data and the high computational cost of training video diffusion models. To address this issue, in this paper, we propose a video-free tuning framework termed ViFeEdit for video diffusion transformers. Without requiring any forms of video training data, ViFeEdit achieves versatile video generation and editing, adapted solely with 2D images. At the core of our approach is an architectural reparameterization that decouples spatial independence from the full 3D attention in modern video diffusion transformers, which enables visually faithful editing while maintaining temporal consistency with only minimal additional parameters. Moreover, this design operates in a dual-path pipeline with separate timestep embeddings for noise scheduling, exhibiting strong adaptability to diverse conditioning signals. Extensive experiments demonstrate that our method delivers promising results of controllable video generation and editing with only minimal training on 2D image data. Codes are available https://github.com/Lexie-YU/ViFeEdit. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_15478 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ViFeEdit: A Video-Free Tuner of Your Video Diffusion Transformer Yu, Ruonan Tan, Zhenxiong Chen, Zigeng Liu, Songhua Wang, Xinchao Computer Vision and Pattern Recognition Diffusion Transformers (DiTs) have demonstrated remarkable scalability and quality in image and video generation, prompting growing interest in extending them to controllable generation and editing tasks. However, compared to the image counterparts, progress in video control and editing remains limited, mainly due to the scarcity of paired video data and the high computational cost of training video diffusion models. To address this issue, in this paper, we propose a video-free tuning framework termed ViFeEdit for video diffusion transformers. Without requiring any forms of video training data, ViFeEdit achieves versatile video generation and editing, adapted solely with 2D images. At the core of our approach is an architectural reparameterization that decouples spatial independence from the full 3D attention in modern video diffusion transformers, which enables visually faithful editing while maintaining temporal consistency with only minimal additional parameters. Moreover, this design operates in a dual-path pipeline with separate timestep embeddings for noise scheduling, exhibiting strong adaptability to diverse conditioning signals. Extensive experiments demonstrate that our method delivers promising results of controllable video generation and editing with only minimal training on 2D image data. Codes are available https://github.com/Lexie-YU/ViFeEdit. |
| title | ViFeEdit: A Video-Free Tuner of Your Video Diffusion Transformer |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.15478 |