ShowFlow: From Robust Single Concept to Condition-Free Multi-Concept Generation

TL;DR

ShowFlow is a novel framework that enables robust, condition-free multi-concept image generation by building on single-concept models and introducing specialized adapters and regularization techniques.

Contribution

The paper introduces ShowFlow, a comprehensive approach with new adapters and training objectives for effective multi-concept image synthesis without extra conditions.

Findings

ShowFlow achieves high-quality multi-concept generation.

It maintains identity and concept fidelity in complex scenarios.

User studies confirm its practical effectiveness.

Abstract

Customizing image generation remains a core challenge in controllable image synthesis. For single-concept generation, maintaining both identity preservation and prompt alignment is challenging. In multi-concept scenarios, relying solely on a prompt without additional conditions like layout boxes or semantic masks, often leads to identity loss and concept omission. In this paper, we introduce ShowFlow, a comprehensive framework designed to tackle these challenges. We propose ShowFlow-S for single-concept image generation, and ShowFlow-M for handling multiple concepts. ShowFlow-S introduces a KronA-WED adapter, which integrates a Kronecker adapter with weight and embedding decomposition, and together with a novel Semantic-Aware Attention Regularization (SAR) training objective to enhance single-concept generation. Building on this foundation, ShowFlow-M directly reuses robust models learned by ShowFlow-S to support multi-concept generation without extra conditions, incorporating a Subject-Adaptive Matching Attention (SAMA) and a Layout Consistency guidance as the plug-and-play module. Extensive experiments and user studies validate ShowFlow's effectiveness, highlighting its potential in real-world applications like advertising and virtual dressing. Our source code will be publicly available at: https://htrvu.github.io/showflow.