Jiří, Philippe Janda (2025) North Bohemia as a Low-Resource Visual Context : Everyday Heritage, Uneven Visibility, and Synthetic Aesthetics. DISEGNO: A DESIGNKULTÚRA FOLYÓIRATA, 9 (1). pp. 108-131. ISSN 2064-7778
|
Text
DISEGNO_IX_01_07_Janda.pdf - Published Version Available under License Creative Commons Attribution Share Alike. Download (8MB) | Preview |
Abstract
Generative AI images are not neutral depictions of place: they translate regions through uneven training data and model priors. Using North Bohemia (Czech Republic) in an “ordinary documentary” 1990s register, this study tests 13 prompts across four models and maps drif t with TDS (8 variables, 0–2). Findings indicate structured drif t: vernacular loss, infrastructural “cleaning,” and stylistic takeover that smooths local memory into globally legible templates—raising questions about everyday heritage visibility in the V4/CEE context.
| Item Type: | Article |
|---|---|
| Uncontrolled Keywords: | #Generative AI; #Central and Eastern Europe (CEE); #North Bohemia; #synthetic aesthetics; #cultural bias; #artistic research; #low-resource contexts |
| Subjects: | N Fine Arts / képzőművészet > N Visual arts (General) For photography, see TR / vizuális művészet általában N Fine Arts / képzőművészet > NX Arts in general / művészetek általában Q Science / természettudomány > QA Mathematics / matematika > QA75 Electronic computers. Computer science / számítástechnika, számítógéptudomány |
| SWORD Depositor: | MTMT SWORD |
| Depositing User: | MTMT SWORD |
| Date Deposited: | 01 Jul 2026 08:20 |
| Last Modified: | 01 Jul 2026 08:20 |
| URI: | https://real.mtak.hu/id/eprint/240969 |
Actions (login required)
 |
Edit Item |
