Computers as co-creative assistants. A comparative study on the use of text-to-image AI models for computer aided conceptual design

This preliminary research presents a comparative study between Text-to-Image AI models and Shape Grammars, one of the main generative approaches to Computer Aided Conceptual Design. The goal is to determine to which extent AI models can reproduce or complement the performance of grammar algorithms as creative support tools for shape exploration in conceptual product design. Workflows, advantages and limitations are identified through a comprehensive practical comparison example. The results show many similarities regarding generative capabilities and highlight several advantages of Text-to-Image AI models, including an easier way of capturing product grammars and a wider and more immediate range of further applications. In contrast, Shape Grammars approach proved more solid in aspects related to exploration workflows and cognitive stimulation. These results encourage the research on new ways to address the interaction between designers and AI generative models, combining the AI potential with well-established generative strategies. [Display omitted] •Text-to-image computational models can identify and produce product brand features.•They constitute a fast method to produce concept variations from existing designs.•They proved efficient tools for creative processes such as concept combination.•Shape Grammars provide better shape exploration and control of brand workflows.•Text-to-image computational models may complement existing generative tools.