FlatMagic: Improving Flat Colorization through AI-driven Design for Digital Comic Professionals
Chuan Yan, John Joon Young Chung, Yoon Kiheon, Yotam I. Gingold, Eytan Adar, Sungsoo Ray Hong
Abstract
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.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 8e35c8e3-cb9b-4a40-83c4-d671d74c4a3dCited by top-tier papers16
- Understanding Design Collaboration Between Designers and Artificial Intelligence: A Systematic Literature ReviewYang Shi, Tian Gao, Xiaohan Jiao, Nan CaoCSCW 2023 · 170 citations
- PromptCharm: Text-to-Image Generation through Multi-modal Prompting and RefinementZhijie Wang, Yuheng Huang, Da Song, Lei Ma et al.CHI 2024 · 111 citations
- PromptPaint: Steering Text-to-Image Generation Through Paint Medium-like InteractionsJohn Joon Young Chung, Eytan AdarUIST 2023 · 94 citations
- "It Felt Like Having a Second Mind": Investigating Human-AI Co-creativity in Prewriting with Large Language ModelsQian Wan, Siying Hu, Yu Zhang, Piaohong Wang et al.CSCW 2024 · 86 citations
- TypeDance: Creating Semantic Typographic Logos from Image through Personalized GenerationShishi Xiao, Liangwei Wang, Xiaojuan Ma, Wei ZengCHI 2024 · 35 citations
Builds on7
- Towards Vivid and Diverse Image Colorization with Generative Color PriorYanze Wu, Xintao Wang, Yu Li, Honglun Zhang et al.ICCV 2021 · 123 citations
- ICONATE: Automatic Compound Icon Generation and IdeationNanxuan Zhao, Nam Wook Kim, Laura Mariah Herman, Hanspeter Pfister et al.CHI 2020 · 49 citations
- EmoG: Supporting the Sketching of Emotional Expressions for StoryboardingYang Shi, Nan Cao, Xiaojuan Ma, Siji Chen et al.CHI 2020 · 48 citations
- Deep Edge-Aware Interactive Colorization against Color-Bleeding EffectsEungyeup Kim, Sanghyeon Lee, Jeonghoon Park, Somi Choi et al.ICCV 2021 · 34 citations
- Instance-Aware Image ColorizationJheng-Wei Su, Hung-Kuo Chu, Jia-Bin HuangCVPR 2020
Related papers
- ShadowMagic: Designing Human-AI Collaborative Support for Comic Professionals' ShadowingAmrita Ganguly, Chuan Yan, John Joon Young Chung, Tong Steven Sun et al.UIST 2024 · 8 citations
- No Pixel Left Behind: Filling Gaps in Anime ColorizationMasahiro Kono, Akinobu Maejima, Yuki Koyama, Yotam Sechayk et al.CHI 2026 · 1 citation
- FlatGAN: A Holistic Approach for Robust Flat-Coloring in High-Definition with Understanding Line DiscontinuityHan Kim, Chunggi Lee, Junsoo Lee, Dohyun Kim et al.ACM MM 2023 · 1 citation
- Exploring Interactive Color Palettes for Abstraction-Driven Exploratory Image ColorizationXinyu Shi, Mingyu Liu, Ziqi Zhou, Ali Neshati et al.CHI 2024 · 9 citations
- AniDoc: Animation Creation Made EasierYihao Meng, Hao Ouyang, Hanlin Wang, Qiuyu Wang et al.CVPR 2025
