SeedEdit: Align Image Re-Generation to Image Editing
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929586938314752 |
|---|---|
| author | Shi, Yichun Wang, Peng Huang, Weilin |
| author_facet | Shi, Yichun Wang, Peng Huang, Weilin |
| contents | We introduce SeedEdit, a diffusion model that is able to revise a given image with any text prompt. In our perspective, the key to such a task is to obtain an optimal balance between maintaining the original image, i.e. image reconstruction, and generating a new image, i.e. image re-generation. To this end, we start from a weak generator (text-to-image model) that creates diverse pairs between such two directions and gradually align it into a strong image editor that well balances between the two tasks. SeedEdit can achieve more diverse and stable editing capability over prior image editing methods, enabling sequential revision over images generated by diffusion models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_06686 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SeedEdit: Align Image Re-Generation to Image Editing Shi, Yichun Wang, Peng Huang, Weilin Computer Vision and Pattern Recognition We introduce SeedEdit, a diffusion model that is able to revise a given image with any text prompt. In our perspective, the key to such a task is to obtain an optimal balance between maintaining the original image, i.e. image reconstruction, and generating a new image, i.e. image re-generation. To this end, we start from a weak generator (text-to-image model) that creates diverse pairs between such two directions and gradually align it into a strong image editor that well balances between the two tasks. SeedEdit can achieve more diverse and stable editing capability over prior image editing methods, enabling sequential revision over images generated by diffusion models. |
| title | SeedEdit: Align Image Re-Generation to Image Editing |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2411.06686 |