EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Bridging Structure and Emotion: A Generative Framework for Accessible and Expressive Knit Design

Jiayin Fan, Li Li

Journal of Design Intelligence · 10.02.2026 · 1 (1) · 39-47

DOI: 10.64509/jdi.11.58 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Design Intelligence, online erschienen am 10.02.2026. Verfasst von Jiayin Fan und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Knit pattern design is challenging, requiring both technical skill and creative vision. We introduce an accessible generative framework using Stable Diffusion fine-tuned with LoRA and an interactive web interface. Our system utilizes a dual-label dataset (over 3000 images) annotated with both technical attributes (stitch type, complexity) and semantic/emotional descriptors (e.g., cozy, elegant) to ensure outputs are structurally coherent and stylistically diverse. The LoRA-tuned model exhibits strong domain specialization, producing clearer stitch definition and fewer non-knitting artifacts than the baseline. We develop an interactive platform featuring an emotion-technical balance slider. This framework positions generative AI as a creative partner that lowers technical barriers and expands the expressive possibilities of textile design.

Zitieren

APA

Fan, J., & Li, L. (2026). Bridging Structure and Emotion: A Generative Framework for Accessible and Expressive Knit Design. Journal of Design Intelligence, 1(1), 39-47. https://doi.org/10.64509/jdi.11.58

Vancouver

Fan J, Li L. Bridging Structure and Emotion: A Generative Framework for Accessible and Expressive Knit Design. Journal of Design Intelligence. 2026;1(1):39-47. doi:10.64509/jdi.11.58

BibTeX
@article{Fan2026,
  author = {Fan, Jiayin and Li, Li},
  title = {Bridging Structure and Emotion: A Generative Framework for Accessible and Expressive Knit Design},
  journal = {Journal of Design Intelligence},
  year = {2026},
  volume = {1},
  number = {1},
  pages = {39--47},
  doi = {10.64509/jdi.11.58}
}
Kostenlos starten →