IRMA-International.org: Creator of Knowledge
Information Resources Management Association
Advancing the Concepts & Practices of Information Resources Management in Modern Organizations

Innovative Applications of Diffusion Models in Visual Style Transformation for Brand Logos

Innovative Applications of Diffusion Models in Visual Style Transformation for Brand Logos
View Sample PDF
Author(s): Yuanzhen Zhao (Xiamen Institute of Technology, China)and Zhensen Liang (City University of Macau, Macau)
Copyright: 2026
Volume: 38
Issue: 1
Pages: 30
Source title: Journal of Organizational and End User Computing (JOEUC)
Editor(s)-in-Chief: Sangbing (Jason) Tsai (International Engineering and Technology Institute (IETI), Hong Kong)and Wei Liu (Qingdao University, China)
DOI: 10.4018/JOEUC.401093

Purchase

View Innovative Applications of Diffusion Models in Visual Style Transformation for Brand Logos on the publisher's website for pricing and purchasing information.

Abstract

Brand logos anchor visual identity, yet adapting them to diverse styles is difficult because geometry, typography, and brand cues must be preserved while appearance changes. The authors present LogoDiffusion-Align (LDA), a diffusion framework with three coordinated modules: Structure-Preserving Control (SPC) constrains shapes and text to prevent geometric drift; Style-Consistent Alignment (SCA) injects learned style tokens to achieve coherent, scene-wide stylization; and a Logo-specific Identity Module (LIM) embeds brand-aware representations to retain distinctive identity features. Across multiple datasets and usage scenarios, LDA outperforms strong diffusion-based baselines including ControlNet, DreamBooth, StyleTokenizer, and InST on both fidelity and identity preservation. In controlled comparisons, LDA attains higher SSIM (0.789 vs. 0.742) and CLIP-Id (0.752 vs. 0.708), while also reducing FID and LPIPS, indicating a more favorable fidelity–perceptual quality trade-off.

Related Content

Sunah Kim, Cheong Kim. © 2026. 31 pages.
Junyuan Wan, Ping Guo, Shiqi Feng, Zichen Liu. © 2026. 24 pages.
Rongjie Qin, Xiaolin Qi, Ying Yuan, Bilal Alatas. © 2026. 27 pages.
Yin Yang, Xingyun Liu, Jorge Luis Cuyubamba Dominguez, Yuan Fang, Wen Xie, Bairong Shen, Keng Leng Siau. © 2026. 31 pages.
Yuxiong Lu, Zhengjie Lou, Xinyi Wang, Xinyi Jia, Chi Zhang. © 2026. 34 pages.
Yuanzhen Zhao, Zhensen Liang. © 2026. 30 pages.
Fandi Wei, Hongtao Luo, Xiaoqian Liu, Min Chen, Xin Zhang, Zheng Liu. © 2026. 24 pages.
Body Bottom