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
ACM CHI Conference on Human Factors in Computing Systems 2022.


PDF (6 MB)

A figure that explains two interaction types, bucketing and tweak. System overview: (a) A line drawing example, (b) Back-end AI-driven flat automation results, (c) Front-end interactions, bucketing (top) and tweak (bottom) in case the segment boundary needs revision, (d) Final results.


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.

Video Overview (2 minutes)

Download as:

Presentation (9 minutes)

Download as:


(or see the ACM Digital Library page)

 author    = {Yan, Chuan and Chung, John Joon Young and Yoon, Kiheon and Gingold, Yotam and Adar, Eytan, and Hong, Sungsoo Ray},
 title     = {{F}lat{M}agic: Improving Flat Colorization through AI-driven Design for Digital Comic Professionals},
 booktitle = {Proceedings of the CHI Conference on Human Factors in Computing Systems},
 series    = {CHI},
 year      = {2022},
 keywords  = {Human-AI collaboration, system for professionals, digital comic colorization, Intermediate Representation, automation and control}