让图像生成既保身份又准对提示，还能无条件生成多概念图
ShowFlow: From Robust Single Concept to Condition-Free Multi-Concept Generation
- 用分解权重与语义注意力正则化提升单概念生成质量
- 复用单概念模型实现无需布局的多概念生成，避免信息丢失
- 适合广告、虚拟试衣等需灵活定制图像的场景
图像定制仍是可控图像合成的核心挑战。单概念生成中，保持身份一致性和提示对齐困难；多概念生成中，仅依赖提示而无布局框或语义掩码时，常导致身份丢失和概念遗漏。本文提出ShowFlow框架，包含ShowFlow-S（单概念）和ShowFlow-M（多概念）。ShowFlow-S采用KronA-WED适配器，结合克罗内克适配器与权重/嵌入分解，并引入新型语义感知注意力正则化训练目标，增强生成质量。在此基础上，ShowFlow-M直接复用ShowFlow-S训练出的鲁棒模型，无需额外条件即可实现多概念生成，通过主体自适应匹配注意力（SAMA）和布局一致性引导作为即插即用模块。大量实验与用户研究验证了其有效性，展现出在广告、虚拟试衣等真实场景的应用潜力。代码将公开于：https://htrvu.github.io/showflow。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。