Design generation, in its essence, is a step-by-step process where designers progressively refine and enhance their work through careful modifications. Despite this fundamental characteristic, existing approaches mainly treat design synthesis as a single-step generation problem, significantly underestimating the inherent complexity of the creative process. To bridge this gap, we propose a novel problem setting called Step-by-Step Layered Design Generation, which tasks a machine learning model with generating a design that adheres to a sequence of instructions from a designer. Leveraging recent advancements in multi-modal LLMs, we propose SLEDGE: Step-by-step LayEred Design GEnerator to model each update to a design as an atomic, layered change over its previous state, while being grounded in the instruction. To complement our new problem setting, we introduce a new evaluation suite, including a dataset and a benchmark. Our exhaustive experimental analysis and comparison with state-of-the-art approaches tailored to our new setup demonstrate the efficacy of our approach. We hope our work will attract attention to this pragmatic and under-explored research area.
@article{arxiv.2512.03335,
title = {Step-by-step Layered Design Generation},
author = {Faizan Farooq Khan and K J Joseph and Koustava Goswami and Mohamed Elhoseiny and Balaji Vasan Srinivasan},
journal= {arXiv preprint arXiv:2512.03335},
year = {2025}
}