Constructing a personalized AI assistant for shear wall layout using Stable Diffusion

TL;DR

This paper introduces a personalized AI assistant for shear wall layout design that leverages Stable Diffusion and Low-Rank Adaptation to generate high-quality, customized structural arrangements efficiently, overcoming limitations of previous methods.

Contribution

The paper presents a novel approach using Stable Diffusion and LoRA for shear wall layout generation, enabling personalized and efficient design with limited data.

Findings

Proven to produce good generative results in shear wall layout

Outperforms heuristic algorithms in speed

Requires less training data than GANs or GNNs

Abstract

Shear wall structures are widely used in high-rise residential buildings, and the layout of shear walls requires many years of design experience and iterative trial and error. Currently, there are methods based on heuristic algorithms, but they generate results too slowly. Those based on Generative Adversarial Networks (GANs) or Graph Neural Networks (GNNs) can only generate single arrangements and require large amounts of training data. At present, Stable Diffusion is being widely used, and by using the Low-Rank Adaptation (LoRA) method to fine-tune large models with small amounts of data, good generative results can be achieved. Therefore, this paper proposes a personalized AI assistant for shear wall layout based on Stable Diffusion, which has been proven to produce good generative results through testing.