Using Generative Adversarial Networks for Conditional Creation of Anime Posters

Abstract

Japanese animation, known as anime, has become one of the most accessible forms of entertainment across globe. Recent advances in generative adversarial networks (GAN) and deep learning have contributed greatly to multiple interesting applications in the domain of anime, particularly in face generation, style transfer, and colorization. However, there are no existing implementations for generating composite anime posters with a genre accompaniment prompt. This work proposes a novel application of genre to anime poster generation conditioned on BERT-tokenized binary genre-tags of light-hearted or heavy-hearted categorized based on the thematic subject content of the medium. A dataset of 9,840 image with genre tags and synopses was constructed by scraping MyAnimeList. The conditional Deep Convolution GAN with Spectral Normalization produced the best posters, achieving the quantitative scores of FID: 90.17, average IS: 3.505, 1KNN with PSNR: 0.445 across inter-label discernability, and FID: 166.4, across genuine versus generated poster distinguishability. The primary contribution of this work is to present results outlining the feasibility of various GAN architectures in synthesizing controllable and complex composite anime posters. The larger implication of this project is to provide an introductory approach showing the promise of a creativity assistant for authors, artists, and animators, where they can simply enter a key phrase representing a concept they have in mind, to generate a baseline idea as an initial phase.