PosBridge: Multi-View Positional Embedding Transplant for Identity-Aware Image Editing

TL;DR

PosBridge introduces a training-free, scalable image editing framework that uses positional embedding transplant to accurately insert objects into scenes, maintaining structural and appearance consistency.

Contribution

The paper presents PosBridge, a novel framework employing positional embedding transplant and Corner Centered Layout for identity-aware image editing without training.

Findings

Outperforms baselines in structural consistency.

Achieves high appearance fidelity.

Offers improved computational efficiency.

Abstract

Localized subject-driven image editing aims to seamlessly integrate user-specified objects into target scenes. As generative models continue to scale, training becomes increasingly costly in terms of memory and computation, highlighting the need for training-free and scalable editing frameworks.To this end, we propose PosBridge an efficient and flexible framework for inserting custom objects. A key component of our method is positional embedding transplant, which guides the diffusion model to faithfully replicate the structural characteristics of reference objects.Meanwhile, we introduce the Corner Centered Layout, which concatenates reference images and the background image as input to the FLUX.1-Fill model. During progressive denoising, positional embedding transplant is applied to guide the noise distribution in the target region toward that of the reference object. In this way, Corner Centered Layout effectively directs the FLUX.1-Fill model to synthesize identity-consistent content at the desired location. Extensive experiments demonstrate that PosBridge outperforms mainstream baselines in structural consistency, appearance fidelity, and computational efficiency, showcasing its practical value and potential for broad adoption.