SeedEdit: Align Image Re-Generation to Image Editing

Yichun Shi, Peng Wang, Weilin Huang
11/11/2024
cs.CV

No confident code implementation found for this paper.

Abstract

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis

89% match2 repos62024

Enhancing Text-to-Image Editing via Hybrid Mask-Informed Fusion

89% match2024

GANTASTIC: GAN-based Transfer of Interpretable Directions for Disentangled Image Editing in Text-to-Image Diffusion Models

89% match2024

Self-Correcting LLM-Controlled Diffusion Models

89% match1 repo1872026

SIGNeRF: Scene Integrated Generation for Neural Radiance Fields

88% match1 repo1292026

Source Prompt Disentangled Inversion for Boosting Image Editability with Diffusion Models

88% match1 repo482026

Cite this paper

@article{shi2024seededit,
  title  = {SeedEdit: Align Image Re-Generation to Image Editing},
  author = {Yichun Shi and Peng Wang and Weilin Huang},
  year   = {2024},
  eprint = {2411.06686},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2411.06686v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2411.06686.svg)](https://codeofpaper.com/paper/2411.06686)

Discussion