SteerFlow: Steering Rectified Flows for Faithful Inversion-Based Image Editing

TL;DR

SteerFlow is a novel, model-agnostic image editing framework that enhances fidelity and control in inversion-based editing by using velocity consistency and adaptive masking.

Contribution

It introduces the Amortized Fixed-Point Solver, Trajectory Interpolation, and Adaptive Masking to improve source fidelity and editing quality in flow-based image editing.

Findings

Achieves better editing quality than existing methods on benchmark datasets.

Maintains high source fidelity with fewer inferences and constraints.

Extends to multi-turn editing without drift.

Abstract

Recent advances in flow-based generative models have enabled training-free, text-guided image editing by inverting an image into its latent noise and regenerating it under a new target conditional guidance. However, existing methods struggle to preserve source fidelity: higher-order solvers incur additional model inferences, truncated inversion constrains editability, and feature injection methods lack architectural transferability. To address these limitations, we propose SteerFlow, a model-agnostic editing framework with strong theoretical guarantees on source fidelity. In the forward process, we introduce an Amortized Fixed-Point Solver that implicitly straightens the forward trajectory by enforcing velocity consistency across consecutive timesteps, yielding a high-fidelity inverted latent. In the backward process, we introduce Trajectory Interpolation, which adaptively blends target-editing and source-reconstruction velocities to keep the editing trajectory anchored to the source. To further improve background preservation, we introduce an Adaptive Masking mechanism that spatially constrains the editing signal with concept-guided segmentation and source-target velocity differences. Extensive experiments on FLUX.1-dev and Stable Diffusion 3.5 Medium demonstrate that SteerFlow consistently achieves better editing quality than existing methods. Finally, we show that SteerFlow extends naturally to a complex multi-turn editing paradigm without accumulating drift.