9791221502893_91.pdf
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...
| Γλώσσα: | English |
|---|---|
| Έκδοση: |
Firenze University Press
2024
|
| Διαθέσιμο Online: | https://books.fupress.com/doi/capitoli/979-12-215-0289-3_91 |
| id |
oapen-20.500.12657-89041 |
|---|---|
| record_format |
dspace |
| spelling |
oapen-20.500.12657-890412024-04-03T02:22:46Z Chapter Generative Design Intuition from the Fine-Tuned Models of Named Architects’ Style Jeong, Hyun Yoo, Youngjin Kim, Youngchae Cha, SeungHyun Lee, Jin-Kook Design Style of Architects Generative AI Image Generation Fine-tuning thema EDItEUR::U Computing and Information Technology::UY Computer science::UYQ Artificial intelligence 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 2024-04-02T15:44:31Z 2024-04-02T15:44:31Z 2023 chapter ONIX_20240402_9791221502893_10 2704-5846 9791221502893 https://library.oapen.org/handle/20.500.12657/89041 eng Proceedings e report application/pdf n/a 9791221502893_91.pdf https://books.fupress.com/doi/capitoli/979-12-215-0289-3_91 Firenze University Press 10.36253/979-12-215-0289-3.91 10.36253/979-12-215-0289-3.91 bf65d21a-78e5-4ba2-983a-dbfa90962870 9791221502893 137 9 Florence open access |
| institution |
OAPEN |
| collection |
DSpace |
| language |
English |
| description |
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 |
| title |
9791221502893_91.pdf |
| spellingShingle |
9791221502893_91.pdf |
| title_short |
9791221502893_91.pdf |
| title_full |
9791221502893_91.pdf |
| title_fullStr |
9791221502893_91.pdf |
| title_full_unstemmed |
9791221502893_91.pdf |
| title_sort |
9791221502893_91.pdf |
| publisher |
Firenze University Press |
| publishDate |
2024 |
| url |
https://books.fupress.com/doi/capitoli/979-12-215-0289-3_91 |
| _version_ |
1799945276993044480 |
