JoJo Anime Character Generation Using Stable Diffusion XL
Experiment on generating anime characters based on the style of JoJo’s Bizarre Adventure using a neural network.
This experiment was a group effort by Group 8 (Kevin, Jion, Min, and Yuki) from the Spring 2024 Pattern Recognition Course at Waseda University. Attributions, credits, and references are provided at the end of the article.
Background
Anime character generation has recently gained significant attention due to its potential to inspire professionals in creating new characters at a reduced animation production cost. Stable Diffusion has emerged as a promising alternative for image synthesis (Guo et al., 2024).
This research project aims to develop an anime character generation model inspired by JoJo’s Bizarre Adventure using Stable Diffusion XL. The goal is to leverage this advanced technology to create original characters that capture JoJo’s dynamic art style and distinctive personality traits.
Research Questions
Based on the background outlined above, we developed our own research questions.
- [Kevin] What impact does the…
