Entrance-end builders writer UI elements to be broadly reusable by parameterizing visible and behavioral properties. Whereas versatile, this makes instantiation more durable, as builders should motive about quite a few property values and interactions. In follow, they need to discover the element’s giant design area and supply reasonable and pure values to properties. To handle this, we introduce distinguishing variations: variations which might be each mimetic and distinct. We body distinguishing variation technology as design-space sampling, combining symbolic inference to establish visually necessary properties with an LLM-driven mimetic sampler to provide reasonable instantiations from its world data. We instantiate distinguishing variations in Celestial, a software that helps builders discover and visualize distinguishing variations. In a examine with front-end builders (n=12), members discovered these variations helpful for evaluating and mapping element design areas, reported that mimetic instantiations had been domain-relevant, and validated that Celestial reworked element instantiation from a handbook course of right into a structured, exploratory exercise.
