# ControlGUI: Guiding Generative GUI Exploration through Perceptual Visual Flow

Source: [ControlGUI: Guiding Generative GUI Exploration through Perceptual Visual Flow](<https://www.sota2.com/research/paper/68fa7b451e209131cea876e1>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-01T05:00:04.436Z

Authors: Aryan Garg, Yue Jiang, Antti Oulasvirta

Published: 2025-02-05T16:25:35.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Multimodal GUI Generation on 1,000-case (test)](<https://www.sota2.com/research/sota/multimodal-gui-generation-on-1-000-case-test.md>): Multimodal GUI Generation; 1,000-case (test); ManIQA: 61.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2502.03330>)

[PDF](<https://arxiv.org/pdf/2502.03330.pdf>)
