无需训练即可实现稳定可控的图像连续编辑，保持原图细节同时精准调节修改强度。
FlowSlider: Training-Free Continuous Image Editing via Fidelity-Steering Decomposition
- 将图像编辑分解为保真度项与导向项，分别负责保留原图结构和引导语义变化。
- 仅缩放导向项即可实现平滑的编辑强度控制，且在多种任务上效果优于现有方法。
- 完全免训练，适合需要快速部署或跨域编辑的应用场景。
连续图像编辑旨在提供类似滑块的编辑强度控制，同时保持源图像的保真度并维持一致的编辑方向。现有基于学习的滑块方法通常依赖于经过合成或代理监督训练的辅助模块，这引入了额外的训练开销，并使滑块行为受限于训练分布，在编辑或领域分布变化时可靠性下降。本文提出 extit{FlowSlider}，一种基于修正流（Rectified Flow）的免训练连续编辑方法，无需任何后训练。 extit{FlowSlider} 将 FlowEdit 的更新分解为 (i) 保真度项，作为源条件化的稳定器以保留身份与结构；(ii) 导向项，驱动语义向目标编辑过渡。几何分析与实证测量表明，这两项近似正交，因此仅缩放导向项而固定保真度项，即可实现稳定的强度控制。结果表明， extit{FlowSlider} 在无需训练的情况下提供了平滑可靠的控制，在多样化任务中显著提升了连续编辑质量。
原文摘要 · Abstract (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 \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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。