Default prefix: Granblue Fantasy

This version of the large model has a more comprehensive set of materials and a more accurate style grasp. It can be directly output without the need for LORA.

Sampler recommendation: Any will do, and it has good applicability.

Recommended number of iterations: around 30

It is recommended to enable high-definition restoration: The zooming algorithm is R-ESRGAN 4x + Anime6B, with a zoom factor of 2 and a re-drawing amplitude of 0.3.

ADetailer is activated. The model recommended is: face_yolov8n.pt

The CFG value is: 5.5 to 7

CLIP recommendation: 2

The generalization is very good. I hope everyone can visit more often and give more likes. Thank you.

View the partial re-displayed image by looking at the picture below.

默认前缀： granblue fantasy

这版大模型比lora版本素材更加全面，风格把握更加准确，无需lora即可直出。

采样器推荐：任意都可以，适用性还不错

迭代步数推荐：30左右

推荐开启高清修复：放大算法为R-ESRGAN 4x+ Anime6B，放大2倍，重绘幅度为0.3

ADetailer开启，AD模型推荐：face_yolov8n.pt，

CFG为：5.5~7

CLIP推荐：2

泛化性很好希望大家多返图多点赞，谢谢

部分返图看下面图