Generating Daylight-driven Architectural Design via Diffusion Models
This work addresses the need for efficient and innovative architectural design tools for architects, though it appears incremental as it builds on existing diffusion and language models.
The paper tackles the problem of AI-aided architectural design by developing a method that generates architectural massing models, integrates daylight-driven facade design for window layouts, and combines large-scale language and text-to-image models for visual renderings, resulting in a system that supports architects' creative inspirations and pioneers new avenues in design development.
In recent years, the rapid development of large-scale models has made new possibilities for interdisciplinary fields such as architecture. In this paper, we present a novel daylight-driven AI-aided architectural design method. Firstly, we formulate a method for generating massing models, producing architectural massing models using random parameters quickly. Subsequently, we integrate a daylight-driven facade design strategy, accurately determining window layouts and applying them to the massing models. Finally, we seamlessly combine a large-scale language model with a text-to-image model, enhancing the efficiency of generating visual architectural design renderings. Experimental results demonstrate that our approach supports architects' creative inspirations and pioneers novel avenues for architectural design development. Project page: https://zrealli.github.io/DDADesign/.