FlowSlider: Training-Free Continuous Image Editing via Fidelity-Steering Decomposition

TL;DR

FlowSlider is a training-free method for continuous image editing that decomposes editing updates into fidelity preservation and semantic steering, enabling stable and reliable control without additional training.

Contribution

It introduces a novel, training-free approach for continuous image editing using Rectified Flow, decomposing updates into orthogonal fidelity and steering components for improved control.

Findings

FlowSlider achieves smooth and reliable editing control.

It requires no post-training or auxiliary modules.

It improves editing quality across diverse tasks.

Abstract

Continuous image editing aims to provide slider-style control of edit strength while preserving source-image fidelity and maintaining a consistent edit direction. Existing learning-based slider methods typically rely on auxiliary modules trained with synthetic or proxy supervision. This introduces additional training overhead and couples slider behavior to the training distribution, which can reduce reliability under distribution shifts in edits or domains. We propose \textit{FlowSlider}, a training-free method for continuous editing in Rectified Flow that requires no post-training. \textit{FlowSlider} decomposes FlowEdit's update into (i) a fidelity term, which acts as a source-conditioned stabilizer that preserves identity and structure, and (ii) a steering term that drives semantic transition toward the target edit. Geometric analysis and empirical measurements show that these terms are approximately orthogonal, enabling stable strength control by scaling only the steering term while keeping the fidelity term unchanged. As a result, \textit{FlowSlider} provides smooth and reliable control without post-training, improving continuous editing quality across diverse tasks.