Latent morphologies: Encoding architectural features and decoding their structure through artificial intelligence

This article explores the impact of Artificial Intelligence (AI) on the architectural discipline, focusing on generative models and their controllability. While generative models have revolutionized the design process by freeing designers from specific tasks and allowing them to focus on desired res...

Full description

Saved in:
Bibliographic Details
Published inInternational journal of architectural computing Vol. 22; no. 3; pp. 353 - 372
Main Author Kim, Dongyun
Format Journal Article
LanguageEnglish
Published London, England SAGE Publications 01.09.2024
Subjects
text-to-image
multimodal
generative AI
machine learning
StyleGAN
Online AccessGet full text

Cover

More Information
Summary:This article explores the impact of Artificial Intelligence (AI) on the architectural discipline, focusing on generative models and their controllability. While generative models have revolutionized the design process by freeing designers from specific tasks and allowing them to focus on desired results, the reliance on randomness frequently hinders controllability and meaningful experimentation. To address this challenge, the article proposes the construction of an encyclopedic architectural dataset, encompassing various architectural projects and combining images with text for multimodal applications and two methodologies, multi-class StyleGAN and multimodal StyleGAN+CLIP to enhance controllability. Utilizing specific conditions, multi-class StyleGAN enables designers to navigate latent space and identify hidden patterns, while StyleGAN+CLIP integrates text to achieve specific controllability and generate diverse architectural features. Through experimentation, the research showcases the potential of generative models to create structured designs that incorporate existing architectural styles.
ISSN:1478-0771
2048-3988
DOI:10.1177/14780771231209458