Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region Control

TL;DR

Follow-Your-Shape introduces a novel shape-aware image editing framework that enables precise, controllable shape modifications while preserving non-target regions, outperforming existing flow-based models especially in large-scale shape transformations.

Contribution

The paper presents a training-free, mask-free method utilizing Trajectory Divergence Maps and Scheduled KV Injection for improved shape editing, along with a new benchmark for evaluation.

Findings

Achieves superior shape editing fidelity and control.

Effectively handles large-scale shape transformations.

Outperforms existing flow-based models in visual quality.

Abstract

While recent flow-based image editing models demonstrate general-purpose capabilities across diverse tasks, they often struggle to specialize in challenging scenarios -- particularly those involving large-scale shape transformations. When performing such structural edits, these methods either fail to achieve the intended shape change or inadvertently alter non-target regions, resulting in degraded background quality. We propose Follow-Your-Shape, a training-free and mask-free framework that supports precise and controllable editing of object shapes while strictly preserving non-target content. Motivated by the divergence between inversion and editing trajectories, we compute a Trajectory Divergence Map (TDM) by comparing token-wise velocity differences between the inversion and denoising paths. The TDM enables precise localization of editable regions and guides a Scheduled KV Injection mechanism that ensures stable and faithful editing. To facilitate a rigorous evaluation, we introduce ReShapeBench, a new benchmark comprising 120 new images and enriched prompt pairs specifically curated for shape-aware editing. Experiments demonstrate that our method achieves superior editability and visual fidelity, particularly in tasks requiring large-scale shape replacement.