SCAPE: Searching Conceptual Architecture Prompts using Evolution
Soo Ling Lim, Peter J Bentley, Fuyuki Ishikawa

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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSemantic Web and Ontologies · Advanced Database Systems and Queries · Service-Oriented Architecture and Web Services
MethodsAttention Is All You Need · Linear Layer · Residual Connection · Layer Normalization · Multi-Head Attention · Byte Pair Encoding · Absolute Position Encodings · Dense Connections · Position-Wise Feed-Forward Layer · Label Smoothing
