Manga2animate creates faithful animations from manga with script and storyboard checks
Manga2Animate: An Agentic Framework for Faithful Manga Animation with Script and Storyboard Planning
Computer Vision and Pattern Recognition
Summary
Turning manga comics into animations is hard because existing methods either ignore the artwork or misunderstand the story layout. The authors developed Manga2Animate, which breaks the task into two steps: making an animation script and then a visual storyboard. Each step is created by one agent and checked by another to make sure it matches the original manga. This teamwork results in animations that better preserve the manga’s characters and storyline.
What this means in practice
- •For animation studios: Generate consistent and accurate animations from manga source material with improved storyline and style preservation.$Commercial implications: Enables studios to automate manga adaptation into quality animation products, reducing manual effort and costs.
- •For comic game developers: Create animated sequences faithful to manga art and story for use in interactive story-driven games.
Authors
Sheng-Wei Zhang, Hsi-An Chen, Yan-Ting Liou, Chih-Hsuan Chen, Shih-Chen Tseng, Yu-Lun Liu
Abstract
Adapting existing manga into coherent animation that stays faithful to the source is a valuable yet challenging task. Existing methods either access the manga mainly through text, losing its characters and art style, or feed manga pages directly into video generation models, which misinterpret the manga's structure and produce incorrect storylines. In this paper, we propose Manga2Animate, a multi-agent framework that grounds every stage of generation in the source manga. We decompose the task into two intermediate representations, an animation script and a visual storyboard. Each representation is produced by a creator agent and reviewed against the source panels by a paired reviewer agent. We tailor representation-specific selection and dual-level feedback to progressively refine both before synthesizing the final animation. Extensive experiments and a user study demonstrate that Manga2Animate produces animations more faithful to the source manga and more consistent across shots than state-of-the-art approaches. Project page: https://annchenn.github.io/Manga2Animate/