用1万多个汉字对比生成模型，揭示速度与画质的权衡。
GANji: A Framework for Introductory AI Image Generation
- 基于10314个汉字数据集，对比VAE、GAN、DDPM三类生成模型。
- DDPM画质最好（FID=26.2），但采样速度慢于其他模型2000倍以上。
- 轻量框架适合教学和研究，直观展示生成模型的性能差异。
生成模型的对比研究通常需要大量计算资源，对研究人员和实践者构成障碍。本文提出 GANji，一个轻量级框架，利用包含10,314个日本汉字的数据集，系统比较变分自编码器（VAE）、生成对抗网络（GAN）和去噪扩散概率模型（DDPM）的性能。结果表明，尽管DDPM在图像保真度上表现最佳（弗雷切特起始距离，FID为26.2），但其采样时间比其他模型慢超过2000倍。GANji框架有效且易于使用，能够清晰揭示模型架构、计算成本与视觉质量之间的根本权衡，适用于教育与研究场景。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。