MS-CustomNet: Controllable Multi-Subject Customization with Hierarchical Relational Semantics

TL;DR

MS-CustomNet introduces a hierarchical, controllable framework for multi-subject text-to-image generation, enabling explicit user-defined arrangements and preserving individual subject identities in complex scenes.

Contribution

The paper presents MS-CustomNet, a novel zero-shot multi-subject customization method with hierarchical spatial control and a new MSI dataset for training complex compositions.

Findings

Achieves a DINO-I score of 0.61 for identity preservation.

Attains a YOLO-L score of 0.94 for spatial control.

Demonstrates superior multi-subject image generation quality.

Abstract

Diffusion-based text-to-image generation has advanced significantly, yet customizing scenes with multiple distinct subjects while maintaining fine-grained control over their interactions remains challenging. Existing methods often struggle to provide explicit user-defined control over the compositional structure and precise spatial relationships between subjects. To address this, we introduce MS-CustomNet, a novel framework for multi-subject customization. MS-CustomNet allows zero-shot integration of multiple user-provided objects and, crucially, empowers users to explicitly define these hierarchical arrangements and spatial placements within the generated image. Our approach ensures individual subject identity preservation while learning and enacting these user-specified inter-subject compositions. We also present the MSI dataset, derived from COCO, to facilitate training on such complex multi-subject compositions. MS-CustomNet offers enhanced, fine-grained control over multi-subject image generation. Our method achieves a DINO-I score of 0.61 for identity preservation and a YOLO-L score of 0.94 for positional control in multi-subject customization tasks, demonstrating its superior capability in generating high-fidelity images with precise, user-directed multi-subject compositions and spatial control.