EUVIMEDEUVIMED entdecken
Open Access · CC BY 3.0

Knowledge-Aware Diffusion Models for Controllable Image Generation With Semantic Layout and Style Decoupling

Yingjie Lu, Hua Zong

International Journal on Semantic Web and Information Systems · 26.08.2026 · 22 (1) · 1-23

DOI: 10.4018/ijswis.419811 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal on Semantic Web and Information Systems, erschienen am 26.08.2026. Verfasst von Yingjie Lu und 1 weiteren Autor:innen. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 3.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the rapid development of diffusion models for digital image generation, achieving stable control over both semantic composition and visual style remains challenging. Existing approaches often rely on implicit attention or direct style injection, which may cause style–content leakage and unstable semantics. To address this issue, the authors propose Palette-Brush Diffusion (PBD), a controllable diffusion framework that decouples style modeling from semantic composition. The palette module models style distributions using whitening transformation and Gram statistics and injects them into diffusion features through affine modulation to preserve texture and color without copying structural content. The brush module separates structural and attribute information in text and maps structural embeddings into spatial layout weights that constrain cross-attention, thus establishing stable semantic–spatial correspondences during diffusion. Experiments demonstrate that PBD achieves more consistent style expression and more stable semantic composition than existing methods.

Zitieren

APA

Lu, Y., & Zong, H. (2026). Knowledge-Aware Diffusion Models for Controllable Image Generation With Semantic Layout and Style Decoupling. International Journal on Semantic Web and Information Systems, 22(1), 1-23. https://doi.org/10.4018/ijswis.419811

Vancouver

Lu Y, Zong H. Knowledge-Aware Diffusion Models for Controllable Image Generation With Semantic Layout and Style Decoupling. International Journal on Semantic Web and Information Systems. 2026;22(1):1-23. doi:10.4018/ijswis.419811

BibTeX
@article{Lu2026,
  author = {Lu, Yingjie and Zong, Hua},
  title = {Knowledge-Aware Diffusion Models for Controllable Image Generation With Semantic Layout and Style Decoupling},
  journal = {International Journal on Semantic Web and Information Systems},
  year = {2026},
  volume = {22},
  number = {1},
  pages = {1--23},
  doi = {10.4018/ijswis.419811}
}
Kostenlos starten →