SCAPE: Searching Conceptual Architecture Prompts using Evolution

TL;DR

SCAPE combines evolutionary algorithms with generative AI to enhance creative exploration in architectural design, significantly improving image novelty and quality through iterative, user-guided mutation and crossover.

Contribution

It introduces a novel method integrating evolutionary search with GPT-4 powered generative AI for creative architectural concept exploration.

Findings

67% increase in image novelty compared to DALL-E 3

24% increase in image novelty within three iterations

Positive feedback from over 20 architects

Abstract

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.