Content style decoupling for multi style image generation using latent diffusion architecture

Chu, Kaiyan and Shang, Yu and Zhang, Lingrui and Yuan, Haiyu (2026) Content style decoupling for multi style image generation using latent diffusion architecture. Scientific Reports. ISSN 2045-2322

Full text not available from this repository.

Abstract

Existing multi-style image generation methods face critical challenges: insufficient content-style decoupling, high computational costs for high-resolution generation, and structural distortion during style transfer. To address these, we propose the Dual-Conditional Lightweight Style Diffusion Model (DCLSDM), a novel approach enhancing content-style decoupling via a dual-conditional control mechanism. This mechanism independently manages content structure and style expression, enabling better control in style transfer. Experimental results on WikiArt and Summer2Winter Yosemite datasets show DCLSDM outperforms comparative models in SSIM, LPIPS, and FID, with significant improvements in inference time, memory usage, and parameter scale-making it suitable for resource-constrained scenarios. It offers an efficient, controllable solution for multi-style image generation, with potential in content creation and digital art production. [Abstract copyright: © 2026. The Author(s).]

Item Type:
Journal Article
Journal or Publication Title:
Scientific Reports
Uncontrolled Keywords:
/dk/atira/pure/subjectarea/asjc/1000
Subjects:
?? multi-style image generationcontent-style decouplingdual-conditional controllightweight modellatent diffusion modelgeneral ??
ID Code:
235434
Deposited By:
Deposited On:
12 Feb 2026 11:50
Refereed?:
Yes
Published?:
Published
Last Modified:
13 Feb 2026 03:05