A Customizable Generator for Comic-Style Visual Narrative

TL;DR

The paper tackles the challenge of generating comics by integrating multiple visual-narrative theories into an end-to-end, modular generator. It encodes Cohn's Visual Narrative Grammar, McCloud's panel transitions, photography-inspired panel compositions, and a circumplex-based action-emotion model across layered components with an API-backed workflow. Key contributions include a modular platform for encoding and testing visual-narrative theories, a structured layer-based pipeline that mirrors comic authors' workflows, and an initial dataset of verbs, symbols, and scenes for demonstration. The work enables visual-narrative authoring and research into computational understanding of sequential art, with extensibility to plug-in plot generators and rendering engines.

Abstract

We present a theory-inspired visual narrative generator that incorporates comic-authoring idioms, which transfers the conceptual principles of comics into system layers that integrate the theories to create comic content. The generator creates comics through sequential decision-making across layers from panel composition, object positions, panel transitions, and narrative elements. Each layer's decisions are based on narrative goals and follow the respective layer idioms of the medium. Cohn's narrative grammar provides the overall story arc. Photographic compositions inspired by the rule of thirds is used to provide panel compositions. McCloud's proposed panel transitions based on focus shifts between scene, character, and temporal changes are encoded in the transition layer. Finally, common overlay symbols (such as the exclamation) are added based on analyzing action verbs using an action-verb ontology. We demonstrate the variety of generated comics through various settings with example outputs. The generator and associated modules could be a useful system for visual narrative authoring and for further research into computational models of visual narrative understanding.

Figures (8)

• Figure 1: Overall software architecture of the generator
• Figure 2: Sequence of operations in the generator
• Figure 3: Sections of the API
• Figure 4: A comic sequence with default randomized settings.
• Figure 5: A comic sequence with actions.