Scholarlink

<p>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.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

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

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年1月29日

查看全文
  • Kaiyan Chu,
  • Yu Shang,
  • Lingrui Zhang,
  • Haiyu Yuan

摘要

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.