|国家预印本平台
首页|ShowFlow: From Robust Single Concept to Condition-Free Multi-Concept Generation

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

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

来源:Arxiv_logoArxiv
英文摘要

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 employs a disentangled learning approach with a novel attention regularization objective to enhance single-concept generation. Building on this foundation, ShowFlow-M directly reuses the learned models from ShowFlow-S to support multi-concept generation without extra conditions, incorporating a Subject-Adaptive Matching Attention (SAMA) and a layout consistency strategy 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.

Trong-Vu Hoang、Quang-Binh Nguyen、Thanh-Toan Do、Tam V. Nguyen、Minh-Triet Tran、Trung-Nghia Le

计算技术、计算机技术

Trong-Vu Hoang,Quang-Binh Nguyen,Thanh-Toan Do,Tam V. Nguyen,Minh-Triet Tran,Trung-Nghia Le.ShowFlow: From Robust Single Concept to Condition-Free Multi-Concept Generation[EB/OL].(2025-06-23)[2025-07-25].https://arxiv.org/abs/2506.18493.点此复制

评论