Target-aware Image Editing via Cycle-consistent Constraints

TL;DR

FlowCycle is a novel image editing framework that creates target-aware intermediate states for more faithful and consistent edits by using cycle-consistent constraints and learnable corruptions.

Contribution

The paper introduces FlowCycle, a flow-based, inversion-free method that optimizes target-aware corruptions through cycle consistency for improved image editing.

Findings

FlowCycle achieves superior editing performance in experiments.

It produces more faithful modifications while maintaining source consistency.

The method is more efficient with dynamic sampling adjustments.

Abstract

Recent pre-trained text-to-image flow models have enabled remarkable progress in text-based image editing. Mainstream approaches adopt a corruption-then-restoration paradigm, where the source image is first corrupted into an editable ``intermediate state'' and then restored to the target image under the prompt guidance. However, current methods construct this intermediate state in a target-agnostic manner, i.e., they mainly focus on realizing source image reconstruction while neglecting the semantic gaps towards the specific editing target. This design inherently results in limited editability or inconsistency when the desired modifications substantially deviate from the source. In this paper, we argue that the intermediate state should be target-aware, i.e., selectively corrupting editing-relevant contents while preserving editing-irrelevant ones. Thus, we propose FlowCycle, an inversion-free and flow-based editing framework that parameterizes corruption with learnable noises and optimizes them through a cycle-consistent process. By iteratively editing the source to the target and recovering back to the source with dual consistency constraints, FlowCycle learns to produce a target-aware intermediate state, enabling faithful modifications while preserving source consistency. For efficiency, we further accelerate the optimization by dynamically adjusting the sampling steps. Extensive ablations demonstrated that FlowCycle achieves superior editing performance.