Move and Act: Enhanced Object Manipulation and Background Integrity for Image Editing

TL;DR

This paper introduces a two-branch, tuning-free image editing method that enhances control over object placement and background preservation during editing, outperforming existing multi-branch approaches.

Contribution

It proposes a novel, simplified two-branch framework for image editing that improves object placement control and background integrity without requiring tuning.

Findings

Effective control over object position during editing

Enhanced background preservation in edited images

Superior editing quality demonstrated through quantitative metrics

Abstract

Current methods commonly utilize three-branch structures of inversion, reconstruction, and editing, to tackle consistent image editing task. However, these methods lack control over the generation position of the edited object and have issues with background preservation. To overcome these limitations, we propose a tuning-free method with only two branches: inversion and editing. This approach allows users to simultaneously edit the object's action and control the generation position of the edited object. Additionally, it achieves improved background preservation. Specifically, we transfer the edited object information to the target area and repair or preserve the background of other areas during the inversion process at a specific time step. In the editing stage, we use the image features in self-attention to query the key and value of the corresponding time step in the inversion to achieve consistent image editing. Impressive image editing results and quantitative evaluation demonstrate the effectiveness of our method. The code is available at https://github.com/mobiushy/move-act.