FlowSlider：基于保真度导向分解的无训练连续图像编辑

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

April 2, 2026

作者: Taichi Endo, Guoqing Hao, Kazuhiko Sumi

cs.AI

摘要

连续图像编辑技术旨在实现滑块式编辑强度控制，同时保持源图像保真度与编辑方向一致性。现有基于学习的滑块方法通常依赖通过合成数据或代理监督训练的辅助模块，这不仅增加了训练开销，更将滑块行为与训练数据分布耦合，导致在编辑任务或领域分布变化时可靠性降低。我们提出FlowSlider——一种基于修正流（Rectified Flow）的无训练连续编辑方法，无需后训练即可实现编辑操作。该方法将FlowEdit的更新过程分解为：(i) 保真项，作为源条件稳定器保持图像身份与结构特征；(ii)导向项，驱动语义向目标编辑方向转变。几何分析与实证测量表明这两项近似正交，通过仅缩放导向项并保持保真项不变，即可实现稳定的强度控制。实验证明FlowSlider能在无需后训练的情况下提供平滑可靠的编辑控制，显著提升跨任务连续编辑质量。

English

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 FlowSlider, a training-free method for continuous editing in Rectified Flow that requires no post-training. 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, FlowSlider provides smooth and reliable control without post-training, improving continuous editing quality across diverse tasks.