From Text to Blueprint: Leveraging Text-to-Image Tools for Floor Plan Creation
Xiaoyu Li, Jonathan Benjamin, Xin Zhang
TL;DR
This study investigates text-to-image synthesis for residential floor-plan design, combining GPT-generated descriptive prompts with diffusion-model pipelines. It compares Stable Diffusion v1.5 to a LoRA-finetuned diffusion model, finding that LoRA’s style-specific fine-tuning yields more detailed and architecturally coherent floorplans, though base SD can produce quicker rough layouts. The approach demonstrates how AI can streamline the design process, generate multiple design options, and support collaboration between architects and clients. The findings suggest a practical path for integrating AI into architectural workflows and point to future work on robustness and broader design styles.
Abstract
Artificial intelligence is revolutionizing architecture through text-to-image synthesis, converting textual descriptions into detailed visual representations. We explore AI-assisted floor plan design, focusing on technical background, practical methods, and future directions. Using tools like, Stable Diffusion, AI leverages models such as Generative Adversarial Networks and Variational Autoencoders to generate complex and functional floorplans designs. We evaluates these AI models' effectiveness in generating residential floor plans from text prompts. Through experiments with reference images, text prompts, and sketches, we assess the strengths and limitations of current text-to-image technology in architectural visualization. Architects can use these AI tools to streamline design processes, create multiple design options, and enhance creativity and collaboration. We highlight AI's potential to drive smarter, more efficient floorplan design, contributing to ongoing discussions on AI integration in the design profession and its future impact.