DesignAID, a generative AI-based tool for fostering creative idea generation, was created to assist designers in tackling large, open-ended problems that require extensive creative exploration and development. By presenting designers with visualizations generated by a text-to-image diffusion model based on their textual descriptions of the design space, DesignAID was able to significantly improve inspiration in comparison to traditional image search and gathering methods. However, as it stands, subsequent iteration on generated inspiration is difficult and requires the user to perform their own prompt engineering. In this project, we aim to address this challenge by creating an intuitive interface for users that allows them to identify key aspects of the system output that inspired them, enabling the user to pass that content forward to iterate and refine the idea space. This improvement should better mesh with the human creative process, furthering the utility of AI to designers.

My favorite part of computers are the people who use them, and through this SuperUROP project, I hope to empower those wonderful humans to achieve their creative aspirations.