메뉴 건너뛰기
.. 내서재 .. 알림
소속 기관/학교 인증
인증하면 논문, 학술자료 등을  무료로 열람할 수 있어요.
한국대학교, 누리자동차, 시립도서관 등 나의 기관을 확인해보세요
(국내 대학 90% 이상 구독 중)
로그인 회원가입 고객센터 ENG
주제분류

추천
검색
질문

논문 기본 정보

자료유형
학술대회자료
저자정보
임은영 (서일대학교)
저널정보
한국실내디자인학회 한국실내디자인학회 학술대회논문집 한국실내디자인학회 2024년도 추계학술발표대회 논문집
발행연도
2024.11
수록면
417 - 420 (4page)

이용수

표지
📌
연구주제
📖
연구배경
🔬
연구방법
🏆
연구결과
AI에게 요청하기
추천
검색
질문

초록· 키워드

오류제보하기
Image generation Artificial Intelligence(AI) is used in the study process of the design initial sketch and concept model, and concept model has positive possibilities for AI software. It takes a lot of time and manpower to implement creative and specialized 3D images in the early stages of design, and the active use of image Generative AI is expected to create better designs and reduce designer labor. This study identifies the shape characteristics of architectural styles by period, inputs existing representative building images as prompts into image-generating AI programs, and designs and executes text prompts corresponding to each architectural style.Instead of inputting commands using text, the existing 3D modeling image was uploaded to create variation and image in the concept direction desired by the user, and the more varied the variation was than the first variation, the more suitable the prompt image was created. As a result of executing a prompt containing eight architectural style keywords in the 3D modeling image, attempts were made to capture the characteristics of each architectural style, but they did not deviate significantly from the form of the existing building. In order to better utilize image Generative AI, the design of prompts is important, and if you clearly write additional visual features of architectural style rather than simple keyword input, you will get various re-imagined options.

목차

Abstract
1. 서론
2. 근·현대 건축스타일
3. 사례분석
4. 결론 및 제언
참고문헌

참고문헌 (0)

참고문헌 신청

함께 읽어보면 좋을 논문

논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!

이 논문과 함께 이용한 논문

최근 본 자료

전체보기

댓글(0)

0