Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models paper https://arxiv.org/abs/2303.04671 co

Variational AutoEncoder 自动编码器（Autoencoder，AE） https://arxiv.org/abs/2003.05991 原理先将高维的原始数据映射到一个低维特征空间，然后从低维特征学习重建原始的数

Using LoRA to quickly fine-tune diffusion models https://github.com/cloneofsimo/lora https://github.com/kohya-ss/sd-s