Litcius/Paper detail

AI Diffusion as Design Vocabulary - Investigating the use of AI image generation in early architectural design and education

Mathias Bank Stigsen, Alexandra Moisi, Shervin Rasoulzadeh, Kristina Schinegger, Stefan Rutzinger

2023eCAADe proceedings10 citationsDOIOpen Access PDF

Abstract

This paper investigates the potential of Text-to-Image AI in assisting the ideation phase in architectural design and education. The study proposes a structured workflow and tests it with first-year architecture students. It aims to create a comprehensive design vocabulary by using AI-generated images as primary design references and incorporating them into a modelling workflow. The paper implements a process combining specific vocabulary extraction, image generation, 2D to 3D translation, and spatial composition within a six weeklong design course. The findings suggest that such a process can enhance the ideation phase by generating new and diverse design inspirations, improve spatial understanding through the exploration of various design elements, and provide students with a targeted visual vocabulary that helps define design intention and streamlines the modelling process.

Topics & Concepts

VocabularyComputer scienceWorkflowProcess (computing)ArchitectureDesign processIdeationHuman–computer interactionArtificial intelligenceNatural language processingEngineeringLinguisticsProgramming languageArtOperations managementPhilosophyPsychologyWork in processVisual artsDatabaseCognitive science3D Surveying and Cultural HeritageArchitecture and Computational DesignBIM and Construction Integration
AI Diffusion as Design Vocabulary - Investigating the use of AI image generation in early architectural design and education | Litcius