Text2Form Diffusion: Framework for learning curated architectural vocabulary

Frederick Chando Kim, Mikhael Johanes, Jeffrey Huang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Stepping towards the machine learning age in architecture, many architects and researchers have developed creative ways of utilizing machine learning with domain-specific architectural datasets in recent years. With the rising popularity of large language-based text-to-image models, architects have relied on different strategies for developing the prompt to create satisfactory images representing architecture, which lessens the agency of the architects in the process. We explore alternative ways of working with such models and put forward the role of designers through the fine-tuning process. This research proses a fine-tuning framework of a pre-trained language model, namely Stable Diffusion, with a dataset of formal architectural vocabularies towards developing a new way of understanding architectural form through human-machine collaboration. This paper explores the creation of an annotation system for machines to learn and understand architectural forms. The results showcased a promising method combining different formal characteristics for architectural form generation and ultimately contributing to the discourse of form and language in architecture in the age of large deep learning models.

Original languageEnglish
Title of host publicationeCAADe 2023 - Digital Design Reconsidered
EditorsWolfgang Dokonal, Urs Hirschberg, Gabriel Wurzer, Gabriel Wurzer
PublisherEducation and research in Computer Aided Architectural Design in Europe
Pages79-88
Number of pages10
ISBN (Print)9789491207341
DOIs
Publication statusPublished - 2023
Event41st Conference on Education and Research in Computer Aided Architectural Design in Europe, eCAADe 2023 - Graz, Austria
Duration: 20 Sept 202322 Sept 2023

Publication series

NameProceedings of the International Conference on Education and Research in Computer Aided Architectural Design in Europe
Volume1
ISSN (Print)2684-1843

Conference

Conference41st Conference on Education and Research in Computer Aided Architectural Design in Europe, eCAADe 2023
Country/TerritoryAustria
CityGraz
Period20/09/2322/09/23

Keywords

  • Architectural Form
  • Diffusion Model
  • Machine Learning
  • Text-to-architecture

Fingerprint

Dive into the research topics of 'Text2Form Diffusion: Framework for learning curated architectural vocabulary'. Together they form a unique fingerprint.

Cite this