HouseTune: Two-Stage Floorplan Generation with LLM Assistance

TL;DR

HouseTune introduces a novel two-stage framework combining LLM reasoning and diffusion models to generate accurate, user-friendly floorplans from natural language descriptions, reducing data requirements and achieving state-of-the-art results.

Contribution

The paper presents a two-stage text-to-floorplan generation method that integrates LLMs with diffusion models, improving accuracy without extensive domain-specific training.

Findings

Achieves state-of-the-art performance across all metrics

Reduces the need for extensive domain-specific training data

Effectively combines reasoning and generative models for floorplan design

Abstract

This paper proposes a two-stage text-to-floorplan generation framework that combines the reasoning capability of Large Language Models (LLMs) with the generative power of diffusion models. In the first stage, we leverage a Chain-of-Thought (CoT) prompting strategy to guide an LLM in generating an initial layout (Layout-Init) from natural language descriptions, which ensures a user-friendly and intuitive design process. However, Layout-Init may lack precise geometric alignment and fine-grained structural details. To address this, the second stage employs a conditional diffusion model to refine Layout-Init into a final floorplan (Layout-Final) that better adheres to physical constraints and user requirements. Unlike prior methods, our approach effectively reduces the difficulty of floorplan generation learning without the need for extensive domain-specific training data. Experimental results demonstrate that our approach achieves state-of-the-art performance across all metrics, which validates its effectiveness in practical home design applications.