Chapter Generative Design Intuition from the Fine-Tuned Models of Named Architects’ Style

This paper suggests the potential application of generative artificial intelligence-based image generation technology in the field of architecture, for early phase shape planning, using the styles of renowned architects. The study employed the following approaches: 1) Intensive image generation base...

Fuld beskrivelse

Saved in:
Bibliografiske detaljer
Main Authors: Jeong, Hyun, Yoo, Youngjin, Kim, Youngchae, Cha, SeungHyun, Lee, Jin-Kook
Format: Online
Sprog:engelsk
Udgivet: Firenze University Press 2024
Fag:
Online adgang:ONIX_20240402_9791221502893_10
Tags: Tilføj Tag
Ingen Tags, Vær først til at tagge denne postø!
Beskrivelse
Summary:This paper suggests the potential application of generative artificial intelligence-based image generation technology in the field of architecture, for early phase shape planning, using the styles of renowned architects. The study employed the following approaches: 1) Intensive image generation based on the styles of 20 architects to test the AI's recognition ability and image quality. 2) Additional training was conducted for architects with low recognition rates to construct an enhanced learning model in the quality of image generation. 3) In addition to generating architectural visualization images using existing architects' design styles, alternative styles were proposed through design combinations, aiming to concretize ambiguous idea communication in the early stages of design and enhance its efficiency. The study sheds light on the future prospects of applying this generative AI model in the field of architecture