Jigsaw: Supporting Designers to Prototype Multimodal Applications by Chaining AI Foundation Models
This addresses a problem for designers by providing a tool to prototype multimodal applications more easily, though it is incremental as it builds on existing foundation models.
The paper tackled the challenge of integrating standalone AI foundation models into creative design processes by introducing Jigsaw, a prototype system that uses puzzle pieces as metaphors to combine models across modalities, resulting in enhanced designer understanding, guidance, and support for exploration and prototyping in a user study.
Recent advancements in AI foundation models have made it possible for them to be utilized off-the-shelf for creative tasks, including ideating design concepts or generating visual prototypes. However, integrating these models into the creative process can be challenging as they often exist as standalone applications tailored to specific tasks. To address this challenge, we introduce Jigsaw, a prototype system that employs puzzle pieces as metaphors to represent foundation models. Jigsaw allows designers to combine different foundation model capabilities across various modalities by assembling compatible puzzle pieces. To inform the design of Jigsaw, we interviewed ten designers and distilled design goals. In a user study, we showed that Jigsaw enhanced designers' understanding of available foundation model capabilities, provided guidance on combining capabilities across different modalities and tasks, and served as a canvas to support design exploration, prototyping, and documentation.