Enhance-A-Video: Better Generated Video for Free
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913709584023552 |
|---|---|
| author | Luo, Yang Zhao, Xuanlei Chen, Mengzhao Zhang, Kaipeng Shao, Wenqi Wang, Kai Wang, Zhangyang You, Yang |
| author_facet | Luo, Yang Zhao, Xuanlei Chen, Mengzhao Zhang, Kaipeng Shao, Wenqi Wang, Kai Wang, Zhangyang You, Yang |
| contents | DiT-based video generation has achieved remarkable results, but research into enhancing existing models remains relatively unexplored. In this work, we introduce a training-free approach to enhance the coherence and quality of DiT-based generated videos, named Enhance-A-Video. The core idea is enhancing the cross-frame correlations based on non-diagonal temporal attention distributions. Thanks to its simple design, our approach can be easily applied to most DiT-based video generation frameworks without any retraining or fine-tuning. Across various DiT-based video generation models, our approach demonstrates promising improvements in both temporal consistency and visual quality. We hope this research can inspire future explorations in video generation enhancement. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_07508 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhance-A-Video: Better Generated Video for Free Luo, Yang Zhao, Xuanlei Chen, Mengzhao Zhang, Kaipeng Shao, Wenqi Wang, Kai Wang, Zhangyang You, Yang Computer Vision and Pattern Recognition DiT-based video generation has achieved remarkable results, but research into enhancing existing models remains relatively unexplored. In this work, we introduce a training-free approach to enhance the coherence and quality of DiT-based generated videos, named Enhance-A-Video. The core idea is enhancing the cross-frame correlations based on non-diagonal temporal attention distributions. Thanks to its simple design, our approach can be easily applied to most DiT-based video generation frameworks without any retraining or fine-tuning. Across various DiT-based video generation models, our approach demonstrates promising improvements in both temporal consistency and visual quality. We hope this research can inspire future explorations in video generation enhancement. |
| title | Enhance-A-Video: Better Generated Video for Free |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.07508 |