Review Using Artificial Intelligence-Generating Images: Exploring Material Ideas from MidJourney to Improve Vernacular Designs

Stephen Tanugraha
{"title":"Review Using Artificial Intelligence-Generating Images: Exploring Material Ideas from MidJourney to Improve Vernacular Designs","authors":"Stephen Tanugraha","doi":"10.24002/jarina.v2i2.7537","DOIUrl":null,"url":null,"abstract":"Artificial Intelligence (AI) was created to be an assistant to humankind. The architectural design process is one of them.   Artificial Intelligence is starting to enter the realm of architecture and design. Lately, teams have developed many AI algorithms to generate random images based on the database they had just by texting a command for them. MidJourney is a discord-based Artificial Intelligence for generating images with the text-to-images method, and its database is infinite; it can suggest incredible things. Architects can use MidJourney as a design ideas generator with specific commands.\n MidJourney, one of the AI pioneers in the design world, still has many shortcomings and limitations. Incorrect details and forms are one of its limitations. This exploration using AI should be deepened as part of MidJourney development. This study aims to discover how far researchers have done the command prompt in exploring MidJourney in architecture. This research can be the basis for further research in developing the text-to-image Artificial Intelligence Generator results. This paper uses a systematic literature review method on journals, books, and websites linked with Artificial Intelligence, architecture, and texture selection for building. The systematic literature review involves collecting questions, identifying keywords, screening articles, analyzing, discussing, and concluding.\n                   The results explain the role of Artificial Intelligence in architectural design. MidJourney can choose the proper material for its innovations by generating concept ideas. However, MidJourney has yet to be able to implement the logic of structures and buildings in its design even though it has used architecture-related prompts, perhaps because it was not specifically designed to produce architectural drawings but graphic design only. The challenge is based on the user defining the limitation and the main ideas for generating Artificial Intelligence.","PeriodicalId":403901,"journal":{"name":"Journal of Artificial Intelligence in Architecture","volume":"55 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Artificial Intelligence in Architecture","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.24002/jarina.v2i2.7537","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

Abstract

Artificial Intelligence (AI) was created to be an assistant to humankind. The architectural design process is one of them.   Artificial Intelligence is starting to enter the realm of architecture and design. Lately, teams have developed many AI algorithms to generate random images based on the database they had just by texting a command for them. MidJourney is a discord-based Artificial Intelligence for generating images with the text-to-images method, and its database is infinite; it can suggest incredible things. Architects can use MidJourney as a design ideas generator with specific commands.  MidJourney, one of the AI pioneers in the design world, still has many shortcomings and limitations. Incorrect details and forms are one of its limitations. This exploration using AI should be deepened as part of MidJourney development. This study aims to discover how far researchers have done the command prompt in exploring MidJourney in architecture. This research can be the basis for further research in developing the text-to-image Artificial Intelligence Generator results. This paper uses a systematic literature review method on journals, books, and websites linked with Artificial Intelligence, architecture, and texture selection for building. The systematic literature review involves collecting questions, identifying keywords, screening articles, analyzing, discussing, and concluding.                    The results explain the role of Artificial Intelligence in architectural design. MidJourney can choose the proper material for its innovations by generating concept ideas. However, MidJourney has yet to be able to implement the logic of structures and buildings in its design even though it has used architecture-related prompts, perhaps because it was not specifically designed to produce architectural drawings but graphic design only. The challenge is based on the user defining the limitation and the main ideas for generating Artificial Intelligence.
回顾使用人工智能生成的图像:探索MidJourney中的材料思想以改进乡土设计
人工智能(AI)被创造出来是为了成为人类的助手。建筑设计过程就是其中之一。人工智能开始进入建筑和设计领域。最近,团队开发了许多人工智能算法,通过向他们发送命令,根据他们拥有的数据库生成随机图像。MidJourney是一个基于不和谐的人工智能,使用文本到图像的方法生成图像,其数据库是无限的;它可以暗示不可思议的事情。建筑师可以使用MidJourney作为具有特定命令的设计想法生成器。MidJourney作为设计领域的AI先驱之一,仍然存在许多缺点和局限性。不正确的细节和形式是它的局限性之一。作为《MidJourney》开发的一部分,这种使用AI的探索应该进一步深化。本研究旨在发现研究人员在探索MidJourney建筑中的命令提示符方面做得有多远。本研究可为进一步研究开发文本到图像的人工智能生成器的成果奠定基础。本文采用系统的文献综述方法,对与人工智能、建筑和建筑纹理选择相关的期刊、书籍和网站进行综述。系统的文献综述包括收集问题、识别关键词、筛选文章、分析、讨论、总结。研究结果解释了人工智能在建筑设计中的作用。《MidJourney》可以通过产生概念想法来选择合适的创新材料。然而,MidJourney虽然使用了与建筑相关的提示,但仍未能在其设计中实现结构和建筑的逻辑,这可能是因为它不是专门为生成建筑图纸而设计的,而只是为了生成平面设计。挑战是基于用户定义的限制和生成人工智能的主要思想。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信