Search papers, labs, and topics across Lattice.
SteerFlow, a model-agnostic image editing framework, improves source fidelity in inversion-based editing by straightening the forward trajectory with an Amortized Fixed-Point Solver and anchoring the backward trajectory using Trajectory Interpolation. Adaptive Masking further enhances background preservation by spatially constraining the editing signal based on concept-guided segmentation and velocity differences. Experiments on FLUX.1-dev and Stable Diffusion 3.5 Medium show SteerFlow achieves superior editing quality and supports multi-turn editing without drift.
Achieve high-fidelity image editing without sacrificing source fidelity by straightening the latent trajectory and adaptively blending source and target velocities.
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.