FlatMagic: Improving Flat Colorization through AI-driven Design for DigitalComic Professionals

Abstract

Creating digital comics involves both creative and menial stages. For example, coloring the image involves many steps, including creative shading but also labor-intensive segmentation. The use of AI can automate this process, but early efforts have revealed limitations–technical and UX–to full automation. Through a study of professionals, we identify `flatting', a stage in digital comic colorization for masking segments of continuous color, as a bottleneck and key target of opportunity for human-guided AI-driven automation. Based on this insight, we built FlatMagic, an interactive, AI-driven flat colorization support tool working on Photoshop. Our user studies found that using FlatMagic significantly reduced professionals’ behavioral and perceived effort versus their current practice. While participants effectively used FlatMagic, we also identified potential constraints in interactions with AI and partially automated workflows. We reflect on implications for comic-focused tools and the benefits and pitfalls of intermediate representations and partial automation.