PositionIC: Unified Position and Identity Consistency for Image Customization

TL;DR

PositionIC introduces a unified framework combining a novel dataset synthesis pipeline and a layout-aware diffusion model to achieve high-fidelity, spatially controllable multi-subject image customization with state-of-the-art results.

Contribution

It presents BMPDS, the first automatic position-annotated dataset synthesis pipeline, and a lightweight diffusion framework with a visibility-aware attention mechanism for precise multi-subject placement.

Findings

Achieves state-of-the-art spatial precision and identity consistency.

Effectively decouples spatial embeddings from semantic features.

Sets new benchmarks in multi-entity image customization.

Abstract

Recent subject-driven image customization excels in fidelity, yet fine-grained instance-level spatial control remains an elusive challenge, hindering real-world applications. This limitation stems from two factors: a scarcity of scalable, position-annotated datasets, and the entanglement of identity and layout by global attention mechanisms. To this end, we introduce PositionIC, a unified framework for high-fidelity, spatially controllable multi-subject customization. First, we present BMPDS, the first automatic data-synthesis pipeline for position-annotated multi-subject datasets, effectively providing crucial spatial supervision. Second, we design a lightweight, layout-aware diffusion framework that integrates a novel visibility-aware attention mechanism. This mechanism explicitly models spatial relationships via an NeRF-inspired volumetric weight regulation to effectively decouple instance-level spatial embeddings from semantic identity features, enabling precise, occlusion-aware placement of multiple subjects. Extensive experiments demonstrate PositionIC achieves state-of-the-art performance on public benchmarks, setting new records for spatial precision and identity consistency. Our work represents a significant step towards truly controllable, high-fidelity image customization in multi-entity scenarios. Code and data: https://github.com/MeiGen-AI/PositionIC.