Powered by OpenAIRE graph
Found an issue? Give us feedback
ZENODOarrow_drop_down
ZENODO
Article . 2026
License: CC BY
Data sources: Datacite
ZENODO
Article . 2026
License: CC BY
Data sources: Datacite
ZENODO
Article . 2026
License: CC BY
Data sources: Datacite
ZENODO
Article . 2026
License: CC BY
Data sources: Datacite
versions View all 4 versions
addClaim

AI-Assisted Manga Creation: A Workflow for Non-Artists

Authors: Mahadi Islam Alif;

AI-Assisted Manga Creation: A Workflow for Non-Artists

Abstract

Making manga has always required years of artistic training — a barrier that has kept countless storytellers from the medium. This paper asks whether generative AI can change that. I developed and tested a five-stage production pipeline that combines large language models for narrative writing with diffusion-based image synthesis for visuals, covering everything from initial story concept through to finished page layout. To validate the approach, I produced a complete five-page manga chapter from scratch — using ChatGPT (OpenAI, 2023), Stable Diffusion (Stability AI, 2022), Midjourney (Midjourney, 2023), and Clip Studio Paint — without any formal drawing training. The results are genuinely encouraging: production time fell dramatically compared to conventional methods, and three independent readers found the chapter coherent and visually engaging. That said, keeping characters visually consistent across panels remained a real struggle, and the emotional depth that comes from a skilled human artist's hand is not something current tools can fully replicate. Beyond the technical findings, this paper engages honestly with the harder questions — what AI-assisted creation means for professional artists, who owns the work, and what it means to call something genuinely creative.

Keywords

Prompt Engineering, Human-Computer Interaction, Sequential Art, Artificial Intelligence, Generative AI, Diffusion Models, Digital Comics, Manga Creation, Creative Automation, Latent Diffusion

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Upload OA version
Are you the author of this publication? Upload your Open Access version to Zenodo!
It’s fast and easy, just two clicks!