SCAPE: Searching Conceptual Architecture Prompts using Evolution
This addresses the need for more creative and explorative design tools for architects, though it is incremental as it builds on existing evolutionary and AI methods.
The paper tackles the problem of limited creativity in generative AI for architectural design by introducing SCAPE, a tool that combines evolutionary algorithms with generative AI, resulting in a 67% improvement in image novelty compared to DALL-E 3 and positive feedback from over 20 architects.
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.