Based on my own taste, this model is fine-tuned by training and fine-tuning about more than 100 pictures of my favorite style.

The base model is a base model based on the original sd v1.5.

Made by merging some excellent light and shadow animation models through merge block weighted.

VAE is the same as Anything v3.0

Most of the parameters of the previewed pictures are based on

• size: 512x768

• sampler: DPM++ SDE Karras

• step: 28

• highfix: true

• Latent 1.5x ~ 2x

• highfix step: 10-20

• highfix denoise: 0.6~0.7

About the name:

This is the model used by a chatbot called alu.