A diffusion-based machine learning method for 3D architectural form-finding

Form-finding is a process in architectural design. Architects create and manipulate the morphology of a building by finding the form using digital tools and algorithms, such as machine learning. Recent research indicates that existing machine learning methods for architectural form-finding are not efficient for training and cannot generate multiple 3D forms under the constraints of users. Therefore, in this research, we develop a method to train and apply low-rank adaptation (LoRA) models in Stable Diffusion (SD) to generate 3D architectural forms based on morphological heat maps. Furthermore, the generated 3D forms can be directly used to precisely control the generation of realistic architectural renderings using pre-trained LoRA and SD models. In conclusion, our method can help architects generate 3D architectural models with consistent renderings. It can serve as a useful tool to improve efficiency and creativity in the architectural design practice of form-finding.