Automatic Generation of Standard Nursing Unit Floor Plan in General Hospital Based on Stable Diffusion

• Published in: Buildings (Basel) 2024-09, Vol.14 (9), p.2601
• Main Authors: Han, Zhuo, Chen, Yongquan
• Format: Article
• Language: English
• Subjects: Architects; Architectural design; Architecture; Artificial intelligence; automatic generation of floor plans; Buildings; Datasets; Deep learning; Diffusion barriers; Floorplans; generative adversarial network; Generative adversarial networks; Hospitals; LoRA fine-turning; Medical research; Model testing; Nurses; Nursing; stable diffusion; standard nursing unit
• ISSN: 2075-5309; 2075-5309
• DOI: 10.3390/buildings14092601

This study focuses on the automatic generation of architectural floor plans for standard nursing units in general hospitals based on Stable Diffusion. It aims at assisting architects in efficiently generating a variety of preliminary plan preview schemes and enhancing the efficiency of the pre-planning stage of medical buildings. It includes dataset processing, model training, model testing and generation. It enables the generation of well-organized, clear, and readable functional block floor plans with strong generalization capabilities by inputting the boundaries of the nursing unit’s floor plan. Quantitative analysis demonstrated that 82% of the generated samples met the evaluation criteria for standard nursing units. Additionally, a comparative experiment was conducted using the same dataset to train a deep learning model based on Generative Adversarial Networks (GANs). The conclusion describes the strengths and limitations of the methodology, pointing out directions for improvement by future studies.