A Generation Method and Evaluation of Architectural Facade Design Using Stable Diffusion with LoRA and ControlNet

초록

This study proposes a novel approach for generating architectural facade images by combining the Stable Diffusion model with Low-RankAdaptation (LoRA) and ControlNet. The standard Stable Diffusion model faces limitations in accurately reflecting architectural elements andmaterial characteristics, which are critical in the design process. To address these challenges, this research integrates domain-specificfine-tuning using LoRA and precise shape control through ControlNet. LoRA allows the model to effectively learn architectural styles anddetails, ensuring better representation of essential design elements such as windows, balconies, and facade materials. Meanwhile, ControlNetutilizes Canny Edge and Depth Map information to enhance shape accuracy and spatial consistency, enabling more reliable image generation. The generated images were evaluated through Contrastive Language-Image Pretraining (CLIP) scores for quantitative analysis andGPT-4V-based qualitative evaluation, providing a more comprehensive understanding of architectural coherence and visual fidelity. TheGPT-4V assessment offered insights into spatial relationships, contextual relevance, and material expression that are not easily capturedthrough traditional metrics. This combined approach reduces the repetitive manual adjustments commonly required in text-prompt-based imagegeneration and facilitates a more intuitive and efficient design process during the early stages of architectural planning. By improving controlover detailed architectural features, the proposed method contributes to the automation of facade design, offering significant potential forreal-world applications in architectural design and visualization. Future research will focus on expanding the dataset to include diversearchitectural styles and validating its practical application in design and construction.

키워드