MoGen: A Unified Collaborative Framework for Controllable Multi-Object Image Generation

TL;DR

MoGen introduces a flexible, multi-object image generation framework that accurately aligns language descriptions with image regions and adaptively integrates multiple control signals for precise, customizable scene creation.

Contribution

The paper presents MoGen, a novel framework with RSA and AMG modules that improve multi-object image generation by enhancing alignment, control flexibility, and scene consistency.

Findings

Outperforms existing methods in generation quality

Achieves higher quantity consistency of objects

Provides superior control flexibility and fine-grained scene customization

Abstract

Existing multi-object image generation methods face difficulties in achieving precise alignment between localized image generation regions and their corresponding semantics based on language descriptions, frequently resulting in inconsistent object quantities and attribute aliasing. To mitigate this limitation, mainstream approaches typically rely on external control signals to explicitly constrain the spatial layout, local semantic and visual attributes of images. However, this strong dependency makes the input format rigid, rendering it incompatible with the heterogeneous resource conditions of users and diverse constraint requirements. To address these challenges, we propose MoGen, a user-friendly multi-object image generation method. First, we design a Regional Semantic Anchor (RSA) module that precisely anchors phrase units in language descriptions to their corresponding image regions during the generation process, enabling text-to-image generation that follows quantity specifications for multiple objects. Building upon this foundation, we further introduce an Adaptive Multi-modal Guidance (AMG) module, which adaptively parses and integrates various combinations of multi-source control signals to formulate corresponding structured intent. This intent subsequently guides selective constraints on scene layouts and object attributes, achieving dynamic fine-grained control. Experimental results demonstrate that MoGen significantly outperforms existing methods in generation quality, quantity consistency, and fine-grained control, while exhibiting superior accessibility and control flexibility. Code is available at: https://github.com/Tear-kitty/MoGen/tree/master.