Controllable GUI Exploration
This addresses the need for designers to rapidly explore large design spaces with low-effort input, though it appears incremental as it builds on existing diffusion methods for a specific domain.
The paper tackles the problem of generating interface sketches during early design stages by proposing a diffusion-based approach that allows flexible control through prompts, wireframes, and visual flows, producing diverse low-fidelity solutions with minimal input effort. It demonstrates qualitative results and shows the model aligns more accurately with specifications than other models.
During the early stages of interface design, designers need to produce multiple sketches to explore a design space. Design tools often fail to support this critical stage, because they insist on specifying more details than necessary. Although recent advances in generative AI have raised hopes of solving this issue, in practice they fail because expressing loose ideas in a prompt is impractical. In this paper, we propose a diffusion-based approach to the low-effort generation of interface sketches. It breaks new ground by allowing flexible control of the generation process via three types of inputs: A) prompts, B) wireframes, and C) visual flows. The designer can provide any combination of these as input at any level of detail, and will get a diverse gallery of low-fidelity solutions in response. The unique benefit is that large design spaces can be explored rapidly with very little effort in input-specification. We present qualitative results for various combinations of input specifications. Additionally, we demonstrate that our model aligns more accurately with these specifications than other models.