Sketch2Manga: Shaded Manga Screening from Sketch with Diffusion Models
This addresses the tedious task of manga creation for artists by automating screentone addition, though it is incremental as it builds on existing deep learning models.
The paper tackles the problem of automatic manga screening by generating shaded screentones from sketches using a diffusion model, achieving significant improvements in quality over existing methods.
While manga is a popular entertainment form, creating manga is tedious, especially adding screentones to the created sketch, namely manga screening. Unfortunately, there is no existing method that tailors for automatic manga screening, probably due to the difficulty of generating high-quality shaded high-frequency screentones. The classic manga screening approaches generally require user input to provide screentone exemplars or a reference manga image. The recent deep learning models enables the automatic generation by learning from a large-scale dataset. However, the state-of-the-art models still fail to generate high-quality shaded screentones due to the lack of a tailored model and high-quality manga training data. In this paper, we propose a novel sketch-to-manga framework that first generates a color illustration from the sketch and then generates a screentoned manga based on the intensity guidance. Our method significantly outperforms existing methods in generating high-quality manga with shaded high-frequency screentones.