OpenCOLE: Towards Reproducible Automatic Graphic Design Generation

Naoto Inoue, Kento Masui, Wataru Shimoda, Kota Yamaguchi; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024, pp. 8131-8135

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.