Existing works focus on fixed-size layout pattern generation, while the more practical free-size pattern generation receives limited attention. In this paper, we propose ChatPattern, a novel Large-Language-Model (LLM) powered framework for flexible pattern customization. ChatPattern utilizes a two-part system featuring an expert LLM agent and a highly controllable layout pattern generator. The LLM agent can interpret natural language requirements and operate design tools to meet specified needs, while the generator excels in conditional layout generation, pattern modification, and memory-friendly patterns extension. Experiments on challenging pattern generation setting shows the ability of ChatPattern to synthesize high-quality large-scale patterns.
@article{arxiv.2403.15434,
title = {ChatPattern: Layout Pattern Customization via Natural Language},
author = {Zixiao Wang and Yunheng Shen and Xufeng Yao and Wenqian Zhao and Yang Bai and Farzan Farnia and Bei Yu},
journal= {arXiv preprint arXiv:2403.15434},
year = {2024}
}