Art Creation with Multi-Conditional StyleGANs

TL;DR

This paper presents a multi-conditional StyleGAN-based approach trained on human paintings to generate realistic artworks with controllable emotional and stylistic features, enhancing artistic synthesis capabilities.

Contribution

It introduces a novel multi-conditional control mechanism and a conditional truncation trick for fine-grained manipulation of generated art characteristics.

Findings

Effective control over emotional and stylistic features in generated paintings

High realism and diversity in synthesized artworks

New evaluation techniques for multi-conditional generation

Abstract

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.