TY - GEN PB - IEEE SP - 01 N1 - This version is the author-accepted manuscript. For information on re-use, please refer to the publisher?s terms and conditions. ID - discovery10196976 Y1 - 2024/08/08/ TI - SCAPE: Searching Conceptual Architecture Prompts using Evolution T3 - IEEE Congress on Evolutionary Computation (CEC) UR - https://doi.org/10.1109/CEC60901.2024.10612168 A1 - Lim, Soo Ling A1 - Bentley, Peter J A1 - Ishikawa, Fuyuki KW - Machine learning algorithms KW - Generative AI KW - Image colour analysis KW - Computational modelling KW - Buildings KW - Evolutionary computation KW - Computer architecture N2 - Conceptual architecture involves a highly creative exploration of novel ideas, often taken from other disciplines as architects consider radical new forms, materials, textures and colors for buildings. While today's generative AI systems can produce remarkable results, they lack the creativity demonstrated for decades by evolutionary algorithms. SCAPE, our proposed tool, combines evolutionary search with generative AI, enabling users to explore creative and good quality designs inspired by their initial input through a simple point and click interface. SCAPE injects randomness into generative AI, and enables memory, making use of the built-in language skills of GPT -4 to vary prompts via text-based mutation and crossover. We demonstrate that compared to DALL. E 3, SCAPE enables a 67% improvement in image novelty, plus improvements in quality and effectiveness of use; we show that in just three iterations SCAPE has a 24% image novelty increase enabling effective exploration, plus optimization of images by users. We use more than 20 independent architects to assess SCAPE, who provide markedly positive feedback. AV - public EP - 08 CY - Yokohama, Japan ER -