OpenCOLE: Towards Reproducible Automatic Graphic Design Generation
This addresses reproducibility barriers for researchers and developers in graphic design automation, but it is incremental as it modifies an existing method.
The paper tackles the problem of reproducibility in automatic graphic design generation by proposing OpenCOLE, an open framework trained on publicly available datasets, and reports performance comparable to the original COLE based on GPT4V evaluations.
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.