Creating meaningful art is often viewed as a uniquely human endeavor. A human artist needs a combination of unique skills, understanding, and genuine intention to create artworks that evoke deep feelings and emotions. In this paper, we introduce a multi-conditional Generative Adversarial Network (GAN) approach trained on large amounts of human paintings to synthesize realistic-looking paintings that emulate human art. Our approach is based on the StyleGAN neural network architecture, but incorporates a custom multi-conditional control mechanism that provides fine-granular control over characteristics of the generated paintings, e.g., with regard to the perceived emotion evoked in a spectator. For better control, we introduce the conditional truncation trick, which adapts the standard truncation trick for the conditional setting and diverse datasets. Finally, we develop a diverse set of evaluation techniques tailored to multi-conditional generation.
@article{arxiv.2202.11777,
title = {Art Creation with Multi-Conditional StyleGANs},
author = {Konstantin Dobler and Florian Hübscher and Jan Westphal and Alejandro Sierra-Múnera and Gerard de Melo and Ralf Krestel},
journal= {arXiv preprint arXiv:2202.11777},
year = {2022}
}