SeedEdit: Align Image Re-Generation to Image Editing
This addresses the challenge of precise image editing for users of diffusion models, though it appears incremental as it builds on existing text-to-image models.
The authors tackled the problem of balancing image reconstruction and re-generation in text-guided image editing, achieving more diverse and stable editing capability compared to prior methods.
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.