Edicho: Consistent Image Editing in the Wild

TL;DR

Edicho introduces a training-free, diffusion-model-based method for consistent image editing across diverse in-the-wild images by leveraging explicit image correspondence and novel guidance strategies.

Contribution

It presents a novel, training-free approach that uses explicit correspondence and refined guidance to achieve consistent editing in complex, real-world images.

Findings

Effective in maintaining consistency across diverse images

Compatible with existing diffusion-based editing methods

Demonstrates superior performance in various settings

Abstract

As a verified need, consistent editing across in-the-wild images remains a technical challenge arising from various unmanageable factors, like object poses, lighting conditions, and photography environments. Edicho steps in with a training-free solution based on diffusion models, featuring a fundamental design principle of using explicit image correspondence to direct editing. Specifically, the key components include an attention manipulation module and a carefully refined classifier-free guidance (CFG) denoising strategy, both of which take into account the pre-estimated correspondence. Such an inference-time algorithm enjoys a plug-and-play nature and is compatible to most diffusion-based editing methods, such as ControlNet and BrushNet. Extensive results demonstrate the efficacy of Edicho in consistent cross-image editing under diverse settings. We will release the code to facilitate future studies.