SNR-Edit: Structure-Aware Noise Rectification for Inversion-Free Flow-Based Editing

TL;DR

SNR-Edit introduces a structure-aware, training-free noise rectification method for flow-based image editing that improves structural fidelity and reduces trajectory drift without model tuning.

Contribution

It proposes a novel, training-free framework that adaptively controls noise to enhance inversion-free image editing with structural preservation.

Findings

Achieves high-fidelity structural preservation in editing tasks.

Delivers competitive pixel-level and VLM-based scores.

Operates with minimal computational overhead (~1s per image).

Abstract

Inversion-free image editing using flow-based generative models challenges the prevailing inversion-based pipelines. However, existing approaches rely on fixed Gaussian noise to construct the source trajectory, leading to biased trajectory dynamics and causing structural degradation or quality loss. To address this, we introduce SNR-Edit, a training-free framework achieving faithful Latent Trajectory Correction via adaptive noise control. Mechanistically, SNR-Edit uses structure-aware noise rectification to inject segmentation constraints into the initial noise, anchoring the stochastic component of the source trajectory to the real image's implicit inversion position and reducing trajectory drift during source--target transport. This lightweight modification yields smoother latent trajectories and ensures high-fidelity structural preservation without requiring model tuning or inversion. Across SD3 and FLUX, evaluations on PIE-Bench and SNR-Bench show that SNR-Edit delivers performance on pixel-level metrics and VLM-based scoring, while adding only about 1s overhead per image.