RESEARCH INTO A STABLE DIFFUSION-BASED HUMAN-MACHINE-HUMAN TEACHING MODEL FOR ARCHITECTURAL DESIGN COURSES

Abstract

ABSTRACT Conventional methods of teaching architectural design have flaws like fuzzy information exchange, limitations of thought dispersion, and disconnection of theory and practice because of the different cognitive levels of teachers and students. This paper explores the interactive and collaborative “human-machine-human” mode of utilizing Stable Diffusion image generation technology to teach architectural design and achieve artificial intelligence. To enhance the quality and effectiveness of instruction, the model uses artificial intelligence for image generation, optimization, and presentation in accordance with the three stages of architectural design teaching that are developed in this paper. Mainly using the Northeastern University youth hostel design course as an example, this paper compares the new “human-machine-human” mode with the traditional “human-human” mode, assesses the necessity and viability of the AI intervention, and offers examples for future architectural course teaching reform and the comprehensive integration of AI and architecture. In the interim, it offers resources and recommendations for the deep integration of AI and architecture, as well as recommendations for future teaching reform of architecture courses.