Multimodal large language models (MLLMs) exhibit remarkable capabilities but remain susceptible to jailbreak attacks exploiting cross-modal vulnerabilities. In this work, we introduce a novel method that leverages sequential comic-style visual narratives to circumvent safety alignments in state-of-the-art MLLMs. Our method decomposes malicious queries into visually innocuous storytelling elements using an auxiliary LLM, generates corresponding image sequences through diffusion models, and exploits the models' reliance on narrative coherence to elicit harmful outputs. Extensive experiments on harmful textual queries from established safety benchmarks show that our approach achieves an average attack success rate of 83.5\%, surpassing prior state-of-the-art by 46\%. Compared with existing visual jailbreak methods, our sequential narrative strategy demonstrates superior effectiveness across diverse categories of harmful content. We further analyze attack patterns, uncover key vulnerability factors in multimodal safety mechanisms, and evaluate the limitations of current defense strategies against narrative-driven attacks, revealing significant gaps in existing protections.

This study presents a theory-inspired visual narrative generative system that integrates conceptual principles-comic authoring idioms-with generative and language models to enhance the comic creation process. Our system combines human creativity with AI models to support parts of the generative process, providing a collaborative platform for creating comic content. These comic-authoring idioms, derived from prior human-created image sequences, serve as guidelines for crafting and refining storytelling. The system translates these principles into system layers that facilitate comic creation through sequential decision-making, addressing narrative elements such as panel composition, story tension changes, and panel transitions. Key contributions include integrating machine learning models into the human-AI cooperative comic generation process, deploying abstract narrative theories into AI-driven comic creation, and a customizable tool for narrative-driven image sequences. This approach improves narrative elements in generated image sequences and engages human creativity in an AI-generative process of comics. We open-source the code at https://github.com/RimiChen/Collaborative_Comic_Generation.

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.