EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Data-Centric LoRA Adaptation and Trustworthy Edge Deployment of a Text-to-Image Diffusion Model for a Rights-Constrained Heritage Domain

Youngho Kim, Hyungwoong Park

Electronics · 16.04.2026 · 15 (8) · 1685

DOI: 10.3390/electronics15081685 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 16.04.2026. Verfasst von Youngho Kim und 1 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Education.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Public deployment of generative AI in cultural institutions is constrained by small, rights-restricted datasets, strict latency and runtime-stability requirements, and limits on visitor-data collection. This study presents a deployment-oriented framework for adapting a pre-trained text-to-image diffusion foundation model to a heritage-specific visual domain using Low-Rank Adaptation (LoRA). A Stable Diffusion v1.5 backbone is specialized through data-centric curation and LoRA fine-tuning, then served through an asynchronous edge architecture that links a Unity client and a local Python (version 3.10) inference server for public-facing operation on a native 400 × 1080 vertical canvas. To support deployment decisions without collecting personally identifiable information, the system records only anonymous operational logs and evaluates sustained-load behavior under repeated inference. In a 1000-iteration profiling test, the proposed configuration maintained stable runtime behavior without observable upward memory drift, with a peak allocated VRAM of 3.04 GB and an average end-to-end latency of 3.12 s. An 8 h field deployment further indicated service continuity under public interaction, while a CLIP-based proxy analysis under matched prompts and seeds suggested improved relative style controllability after adaptation (0.848 vs. 0.799). Rather than claiming cultural authenticity or visitor-level effects, this study offers a data-centric, deployment-oriented methodology for operating public-facing generative AI under small-data, latency, and privacy constraints.

Förderung

  • Ministry of Education

Zitieren

APA

Kim, Y., & Park, H. (2026). Data-Centric LoRA Adaptation and Trustworthy Edge Deployment of a Text-to-Image Diffusion Model for a Rights-Constrained Heritage Domain. Electronics, 15(8), 1685. https://doi.org/10.3390/electronics15081685

Vancouver

Kim Y, Park H. Data-Centric LoRA Adaptation and Trustworthy Edge Deployment of a Text-to-Image Diffusion Model for a Rights-Constrained Heritage Domain. Electronics. 2026;15(8):1685. doi:10.3390/electronics15081685

BibTeX
@article{Kim2026,
  author = {Kim, Youngho and Park, Hyungwoong},
  title = {Data-Centric LoRA Adaptation and Trustworthy Edge Deployment of a Text-to-Image Diffusion Model for a Rights-Constrained Heritage Domain},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {8},
  pages = {1685},
  doi = {10.3390/electronics15081685}
}
Kostenlos starten →