InsEdit: Towards Instruction-based Visual Editing via Data-Efficient Video Diffusion Models Adaptation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914462952325120 |
|---|---|
| author | Rao, Zhefan Zou, Bin Che, Haoxuan He, Xuanhua Choi, Chong Hou Li, Yanheng Liu, Rui Chen, Qifeng |
| author_facet | Rao, Zhefan Zou, Bin Che, Haoxuan He, Xuanhua Choi, Chong Hou Li, Yanheng Liu, Rui Chen, Qifeng |
| contents | Instruction-based video editing is a natural way to control video content with text, but adapting a video generation model into an editor usually appears data-hungry. At the same time, high-quality video editing data remains scarce. In this paper, we show that a video generation backbone can become a strong video editor without large scale video editing data. We present InsEdit, an instruction-based editing model built on HunyuanVideo-1.5. InsEdit combines a visual editing architecture with a video data pipeline based on Mutual Context Attention (MCA), which creates aligned video pairs where edits can begin in the middle of a clip rather than only from the first frame. With only O(100)K video editing data, InsEdit achieves state-of-the-art results among open-source methods on our video instruction editing benchmarks. In addition, because our training recipe also includes image editing data, the final model supports image editing without any modification. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_08646 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | InsEdit: Towards Instruction-based Visual Editing via Data-Efficient Video Diffusion Models Adaptation Rao, Zhefan Zou, Bin Che, Haoxuan He, Xuanhua Choi, Chong Hou Li, Yanheng Liu, Rui Chen, Qifeng Computer Vision and Pattern Recognition Instruction-based video editing is a natural way to control video content with text, but adapting a video generation model into an editor usually appears data-hungry. At the same time, high-quality video editing data remains scarce. In this paper, we show that a video generation backbone can become a strong video editor without large scale video editing data. We present InsEdit, an instruction-based editing model built on HunyuanVideo-1.5. InsEdit combines a visual editing architecture with a video data pipeline based on Mutual Context Attention (MCA), which creates aligned video pairs where edits can begin in the middle of a clip rather than only from the first frame. With only O(100)K video editing data, InsEdit achieves state-of-the-art results among open-source methods on our video instruction editing benchmarks. In addition, because our training recipe also includes image editing data, the final model supports image editing without any modification. |
| title | InsEdit: Towards Instruction-based Visual Editing via Data-Efficient Video Diffusion Models Adaptation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.08646 |