International Journal of Film and Media Arts

A Multimodal Framework For Automated Background Music Generation In Japanese Manga Using Large Language Models

Megha Sharma, Muhammad Taimoor Haseeb, Gus Xia, Yoshimasa Tsuruoka — Sat, 30 May 2026 00:00:00 +0000

Recent waves of digitization have introduced a new form of enjoying comics: with music. We begin our analysis of this movement by discussing the multifarious modes of pairing music and comics as well as how music-comic pairs are received by readers and scholars. Our literature review reveals that this new movement has been growing sluggishly due to the time, effort, and cost required to produce music centered around the detailed story of a comic. In this work, we present a possible approach of using generative AI to automate the background music generation. The biggest challenge in this task is the lack of available data or a baseline. After extensive experimentation, we propose an audio generation pipeline that produces background music for an input manga (Japanese comic) book. By incorporating scene segmentation, longer context, and prompt engineering, we create a novel reading experience for manga readers by adding music as an additional stimulus. The pipeline begins with using the dialogues in a manga to detect scene boundaries and perform emotion classification using the characters’ faces within a scene. Then, we use GPT-4o to translate this low-level scene information into a high-level music directive. Conditioned on the scene information and the music directive, another instance of GPT-4o generates page-level music captions to guide a state-of-the-art text-to-music model. This produces music that is aligned with the manga’s evolving narrative. In a subjective evaluation, we find that participants prefer the proposed pipeline more than the baseline pipeline by a statistically significant margin across the metrics of relevancy, quality, and consistency. In particular, we find that our pipeline’s largest contribution comes in providing consistency across pages as well as generating efficient text prompts for the music generation step. Alongside our development, ethical risks of generative AI in affecting transparency, bias, access and exploitation were examined and mitigated where possible. We provide output samples of the pipeline at: manga-to-music.github.io/M2M-Gen/

Keywords: Manga, Multimodal Analysis, Digital Comics, Generative AI, Content-Based Music Generation

A Comic Is a Comic Is a Comic: Exploring Prototypes, Parameters, and (Post)Digital Comics

Giorgio Busi Rizzi — Sat, 30 May 2026 00:00:00 +0000

The history of comics has seen countless variations, yet its most fundamental elements have long remained relatively consistent: paper, a combination of text and drawn images, panel layouts, the narrative sequence. Digital comics, however, have more conspicuously hybridized the affordances of the medium, reconfiguring its materiality and semiotic space, possibly integrating multimedia elements, hyperlinks, animations, and game-like features.

In response, certain scholars have strengthened the boundaries of print comics to exclude (some) digital instances; yet the issue invariably confronts the field’s longstanding resistance to definition and the polarization of theoretical positions around the elusive idea of comicsness.

This paper engages with this debate by proposing a framework for identifying a set of parameterized characteristics that define prototypical comics, situating digital comics at the periphery of the medium in reason of differences in reading protocols and the types of agency afforded.

Three-Dimensional Panel Arrangements in Augmented, Virtual and Mixed Reality Comics

Daniel Goodbrey, David John Tree — Sat, 30 May 2026 00:00:00 +0000

Digital comics are commonly read on the screens of smartphones, tablets and personal computers. The popularity and widespread adoption of these devices have driven the development of apps, games and experiences utilising augmented, virtual and mixed reality technology. Alongside this rise in popularity, the digital mediation and hybridisation of the form of comics have allowed for the creation of comic formats designed to be read and navigated in three dimensions via these technologies.

This article provides a practice-based examination of the use of three-dimensional panel arrangements within digitally mediated comics. Case studies are provided from a range of prototypes that were created by the authors to explore the use of augmented, virtual and mixed reality in digital comic delivery. The design and analysis of these prototypes draws on existing theory and practice established around comics and their mediation in print, digital and architectural formats.

The article considers the use of tropes appropriated from the architectural and digital mediation of the comics’ form. It highlights the ways in which narrative effect can be created by the relative position in three-dimensional space between reader and panel sequence. The tension between the fixed sequences of comics’ narrative and the freeform exploration of three-dimensional space is also examined. Finally, the article examines how spatial depth impacts on the reader’s experience of panel sequences and the layout and navigational challenges this raises.

Key words: Comics, Digital Mediation, Virtual Reality, Augmented Reality, Mixed Reality

The Artificial Cartoonist: Key Characteristics Of AI-Assisted Sequential Storytelling

Erik Barkman — Sat, 30 May 2026 00:00:00 +0000

Since early 2022, AI image generators have made it possible for anyone to create comic-like sequential narratives, no drawing skills required. However, after an initial flurry of interest among creators and readers, so-called “AI comics” now seem to garner limited attention outside the realm of avantgarde experimentation.

This article offers a brief introduction to the form before moving into a close reading of two specific comics, one AI-generated, one human-made, informed by Mikkonen and Braithwaite’s concept of Figural Solidarity. Contrasting the two comics teases out characteristics of AI-generated visual storytelling which, judging by their reappearance in multiple other comics created with the help of generative AI, seem to stem from inherent limitations of the image generators themselves.

The article discusses how these characteristics may affect the reading experience and perhaps even the limited popularity of “AI comics”, and what, knowing what we now know, we may surmise about the future of the artificial or artificially enhanced cartoonist.

Keywords: AI, AI comics, comics analysis, sequential storytelling, iconic solidarity, figural solidarity

From Panel To Pulse: Aurality, Closure, and Reader Agency

Chris Lambert — Sat, 30 May 2026 00:00:00 +0000

This paper examines the integration of audible sound into the traditionally silent medium of comics, analysing how emerging technologies reshape narrative structure, reader agency, and sensory experience. Drawing on theories of closure, intermediality, and visual semiotics, it evaluates historical and contemporary forms including motion comics, Webtoons, AR/VR comics, and audio comics. The study argues that synchronised or prescriptive sound often disrupts reader-controlled pacing and imaginative participation, undermining the core mechanics of comics reading. In contrast, fluid, atmospheric, and non-diegetic sound design can enhance immersion while preserving interpretive openness. Case studies demonstrate that successful sonic integration occurs when sound complements rather than dictates visual rhythm. The paper concludes that sound should function as an augmentative layer within comics, the notable exception being the fully sonic ‘audio comic’ which operates as a distinct mode of narrative construction.

Keywords: audible comics, aurality, digital comics, intermediality, closure, Webtoons

Table of Contents and Editorial

Pedro Moura, Marco Fraga da Silva — Sat, 30 May 2026 00:00:00 +0000

The editorial of this issue of the International Journal of Film and Media Arts explores the evolving relationship between comics and technology, arguing that comics have always been deeply intertwined with technological systems. Rather than viewing digital tools and artificial intelligence as disruptive breaks from tradition, the editors frame them as intensifications of a long-standing coevolution between comics production, circulation, and technological mediation. Drawing on perspectives from media theory, cognition studies, and platform capitalism, the editorial reflects on how contemporary technologies increasingly shape creative labour, reader experience, and cultural production.

The issue situates comics within broader debates surrounding automation, AI-assisted creativity, digital infrastructures, and the reorganisation of labour under computational systems. At the same time, it emphasises that comics are not passive recipients of technological change, but active sites where new forms of narrative, spatiality, sound, and multimodal interaction emerge.

The collection brings together interdisciplinary contributions examining topics such as digital comics theory, augmented and virtual reality comics, AI-generated music for manga, AI-assisted sequential storytelling, and the integration of sound technologies into comics reading experiences. Across these studies, the issue highlights how comics and technology continually reshape one another aesthetically, materially, and socially.

Ultimately, the editorial presents comics as a dynamic and technologically mediated art form whose future lies in hybrid experimentation, critical reflection, and the ongoing negotiation between human creativity and digital systems.