Towards the Automatic Anime Characters Creation with Generative Adversarial Networks

TL;DR

This paper develops a specialized GAN model for high-quality anime facial image generation, addressing data quality and model stability issues, and provides an accessible online tool for anime character creation.

Contribution

It introduces a well-curated anime facial dataset and applies DRAGAN for stable training, resulting in a practical tool for automatic anime character generation.

Findings

Achieved stable, high-quality anime facial image generation

Demonstrated effectiveness of DRAGAN in training GANs on anime data

Launched an accessible online platform for anime character creation

Abstract

Automatic generation of facial images has been well studied after the Generative Adversarial Network (GAN) came out. There exists some attempts applying the GAN model to the problem of generating facial images of anime characters, but none of the existing work gives a promising result. In this work, we explore the training of GAN models specialized on an anime facial image dataset. We address the issue from both the data and the model aspect, by collecting a more clean, well-suited dataset and leverage proper, empirical application of DRAGAN. With quantitative analysis and case studies we demonstrate that our efforts lead to a stable and high-quality model. Moreover, to assist people with anime character design, we build a website (http://make.girls.moe) with our pre-trained model available online, which makes the model easily accessible to general public.