Inverse-and-Edit: Effective and Fast Image Editing by Cycle Consistency Models

TL;DR

This paper introduces a cycle-consistency based framework that significantly improves high-fidelity image inversion and editing efficiency, achieving state-of-the-art results with only four steps, thus enabling precise and controllable image editing.

Contribution

We propose a novel cycle-consistency optimization strategy that enhances inversion quality and editing control in a fast, four-step process, surpassing previous diffusion-based methods.

Findings

State-of-the-art performance on various editing tasks

High-quality inversion with only four steps

Efficient editing matching full diffusion models

Abstract

Recent advances in image editing with diffusion models have achieved impressive results, offering fine-grained control over the generation process. However, these methods are computationally intensive because of their iterative nature. While distilled diffusion models enable faster inference, their editing capabilities remain limited, primarily because of poor inversion quality. High-fidelity inversion and reconstruction are essential for precise image editing, as they preserve the structural and semantic integrity of the source image. In this work, we propose a novel framework that enhances image inversion using consistency models, enabling high-quality editing in just four steps. Our method introduces a cycle-consistency optimization strategy that significantly improves reconstruction accuracy and enables a controllable trade-off between editability and content preservation. We achieve state-of-the-art performance across various image editing tasks and datasets, demonstrating that our method matches or surpasses full-step diffusion models while being substantially more efficient. The code of our method is available on GitHub at https://github.com/ControlGenAI/Inverse-and-Edit.