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.
Mahadi Islam Alif (Sat,) studied this question.