Using text-to-image generation for architectural design ideation

TLDR

Text‑to‑image generation has gained popularity across creative domains. The study examines how text‑to‑image generators can support creativity in early architectural design. A laboratory study with 17 architecture students used Midjourney, Stable Diffusion, and DALL‑E to develop a culture‑center concept. Image generation proved useful when design constraints are considered, fostering serendipitous idea discovery and an imaginative mindset, though challenges exist; understanding its limits enables architects to leverage the technology for innovation and clearer concept communication.

Abstract

Text-to-image generation has become very popular in various domains requiring creativity. This article investigates the potential of text-to-image generators in supporting creativity during the early stages of the architectural design process. We conducted a laboratory study with 17 architecture students, who developed a concept for a culture center using three popular text-to-image generators: Midjourney, Stable Diffusion, and DALL-E. Through standardized questionnaires and group interviews, we found that image generation could be a meaningful part of the design process when design constraints are carefully considered. Generative tools support serendipitous discovery of ideas and an imaginative mindset, enriching the design process. We identified several challenges of image generators and provided considerations for software development and educators to support creativity and emphasize designers’ imaginative mindset. By understanding the limitations and potential of text-to-image generators, architects and designers can leverage this technology in their design process and education, facilitating innovation and effective communication of concepts.