FlatMagic: Improving Flat Colorization through AI-driven Design for Digital Comic Professionals
Chuan Yan, John Joon Young Chung, Kiheon Yoon, Yotam Gingold, Eytan Adar, Sungsoo Ray Hong
Creating digital comics involves multiple stages, some creative and some menial. For example, coloring a comic requires a labor-intensive stage known as 'flatting,' or masking segments of continuous color, as well as creative shading, lighting, and stylization stages. The use of AI can automate the colorization process, but early efforts have revealed limitations-technical and UX-to full automation. Via a formative study of professionals, we identify flatting 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 for Photoshop. Our user studies found that using FlatMagic significantly reduced professionals' real 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 in designing human-AI collaboration tools for professionals.
Pre-print: PDF, (6.3 MB), to appear, CHI'22