SimInversion: A Simple Framework for Inversion-Based Text-to-Image Editing

TL;DR

SimInversion introduces a novel approach to text-guided image editing by optimizing DDIM inversion, reducing approximation errors, and improving editing accuracy without increasing computational costs.

Contribution

It proposes disentangling guidance scales for source and target images in DDIM inversion, enhancing editing performance while maintaining efficiency.

Findings

Significant improvement in image editing quality on PIE-Bench

Theoretically derived optimal guidance scale of 0.5

Enhanced DDIM inversion accuracy without added computational cost

Abstract

Diffusion models demonstrate impressive image generation performance with text guidance. Inspired by the learning process of diffusion, existing images can be edited according to text by DDIM inversion. However, the vanilla DDIM inversion is not optimized for classifier-free guidance and the accumulated error will result in the undesired performance. While many algorithms are developed to improve the framework of DDIM inversion for editing, in this work, we investigate the approximation error in DDIM inversion and propose to disentangle the guidance scale for the source and target branches to reduce the error while keeping the original framework. Moreover, a better guidance scale (i.e., 0.5) than default settings can be derived theoretically. Experiments on PIE-Bench show that our proposal can improve the performance of DDIM inversion dramatically without sacrificing efficiency.