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

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.

Figures (15)

• Figure 1: FlowSlider for continuous image editing: A slider-style editing framework that requires no learning and can be applied instantly to any edit. Simply specify a prompt pair to continuously control the editing intensity via the scaling parameter $s$. Each row shows progressively stronger editing results starting from the real image.
• Figure 2: 'Autumn $\rightarrow$ Winter' editing example. Naive scaling in FlowEdit Kulikov_2025_ICCV introduces artifacts at $s=2$, whereas FlowSlider maintains stable fidelity. Note that our FlowSlider is identical to FlowEdit when $s=1$.
• Figure 3: Fidelity--steering decomposition and its implication for strength control.(a) Exact decomposition of the FlowEdit update into a same-state, cross-prompt steering term and a same-prompt, cross-state fidelity term: $V^{\Delta}=V_{\mathrm{fid}}+V_{\mathrm{steer}}$. (b) Naive scaling ($sV^{\Delta}$) magnifies both components and residual non-cancelled noise, which can drive the trajectory out of the source-consistent regime; decomposed scaling $V^{\Delta}_{s}=V_{\mathrm{fid}}+sV_{\mathrm{steer}}$ increases semantic strength while keeping source-conditioned stabilization unchanged.
• Figure 4: Orthogonality between fidelity and steering components on our benchmark data. We plot the angle $\theta(t) = \arccos( \frac{\langle V_{\mathrm{fid}}(t),V_{\mathrm{steer}}(t)\rangle}{\|V_{\mathrm{fid}}(t)\|\,\|V_{\mathrm{steer}}(t)\|})$ across timesteps and strength settings. Angles remain concentrated near $90^\circ$, indicating weak coupling between source-conditioned stabilization and semantic steering.
• Figure 5: Qualitative slider results. We compare our method against Kontinuous Kontext parihar2025kontinuouskontext and SliderEdit zarei2025slideredit. Each row shows the original (leftmost) and edited outputs at increasing slider strengths (left to right).