Saved in:
Bibliographic Details
Main Authors: Hamel, Chandon, Busch, Mike
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.24128
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918150090522624
author Hamel, Chandon
Busch, Mike
author_facet Hamel, Chandon
Busch, Mike
contents The comparative study of generative models often requires significant computational resources, creating a barrier for researchers and practitioners. This paper introduces GANji, a lightweight framework for benchmarking foundational AI image generation techniques using a dataset of 10,314 Japanese Kanji characters. It systematically compares the performance of a Variational Autoencoder (VAE), a Generative Adversarial Network (GAN), and a Denoising Diffusion Probabilistic Model (DDPM). The results demonstrate that while the DDPM achieves the highest image fidelity, with a Fréchet Inception Distance (FID) score of 26.2, its sampling time is over 2,000 times slower than the other models. The GANji framework is an effective and accessible tool for revealing the fundamental trade-offs between model architecture, computational cost, and visual quality, making it ideal for both educational and research purposes.
format Preprint
id arxiv_https___arxiv_org_abs_2509_24128
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GANji: A Framework for Introductory AI Image Generation
Hamel, Chandon
Busch, Mike
Computer Vision and Pattern Recognition
The comparative study of generative models often requires significant computational resources, creating a barrier for researchers and practitioners. This paper introduces GANji, a lightweight framework for benchmarking foundational AI image generation techniques using a dataset of 10,314 Japanese Kanji characters. It systematically compares the performance of a Variational Autoencoder (VAE), a Generative Adversarial Network (GAN), and a Denoising Diffusion Probabilistic Model (DDPM). The results demonstrate that while the DDPM achieves the highest image fidelity, with a Fréchet Inception Distance (FID) score of 26.2, its sampling time is over 2,000 times slower than the other models. The GANji framework is an effective and accessible tool for revealing the fundamental trade-offs between model architecture, computational cost, and visual quality, making it ideal for both educational and research purposes.
title GANji: A Framework for Introductory AI Image Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.24128