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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Hoang, Trong-Vu, Nguyen, Quang-Binh, Do, Thanh-Toan, Nguyen, Tam V., Tran, Minh-Triet, Le, Trung-Nghia
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911621668929536
author Hoang, Trong-Vu
Nguyen, Quang-Binh
Do, Thanh-Toan
Nguyen, Tam V.
Tran, Minh-Triet
Le, Trung-Nghia
author_facet Hoang, Trong-Vu
Nguyen, Quang-Binh
Do, Thanh-Toan
Nguyen, Tam V.
Tran, Minh-Triet
Le, Trung-Nghia
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_18493
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ShowFlow: From Robust Single Concept to Condition-Free Multi-Concept Generation
Hoang, Trong-Vu
Nguyen, Quang-Binh
Do, Thanh-Toan
Nguyen, Tam V.
Tran, Minh-Triet
Le, Trung-Nghia
Computer Vision and Pattern Recognition
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.
title ShowFlow: From Robust Single Concept to Condition-Free Multi-Concept Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.18493