OpenCOLE: Towards Reproducible Automatic Graphic Design Generation

TL;DR

OpenCOLE introduces an open framework for automatic graphic design generation, utilizing publicly available datasets and a modified COLE model, promoting reproducibility and open development in the field.

Contribution

It presents a reproducible, open-source graphic design generation framework based on a modified COLE model trained on public datasets.

Findings

Model achieves performance comparable to original COLE

Pipeline and training results are publicly released

Encourages open development in graphic design AI

Abstract

Automatic generation of graphic designs has recently received considerable attention. However, the state-of-the-art approaches are complex and rely on proprietary datasets, which creates reproducibility barriers. In this paper, we propose an open framework for automatic graphic design called OpenCOLE, where we build a modified version of the pioneering COLE and train our model exclusively on publicly available datasets. Based on GPT4V evaluations, our model shows promising performance comparable to the original COLE. We release the pipeline and training results to encourage open development.