HEZI_ Cloudtop Chessboard XL<HEZI_云顶棋盘xl>

VAE recommendation: vae-ft-mse-840000-ema-pruned.safetensors

Sampler recommendation: DPM++ 2M Karras

Recommended number of iterations: 30

It is recommended to enable high-definition restoration: the enlargement algorithm is R-ESRGAN 4x + Anime6B, with a 2x enlargement and a redrawing intensity of 0.6.

ADetailer is enabled. AD model recommended: face_yolov8s.pt

Recommended Lora weight: 0.7

The CFG is: 5.5 to 7.

CLIP Recommendation: 2

It has excellent generalization and can be combined with other LoRAs. I hope everyone can share more pictures and give more likes. Thank you!

VAE推荐开：vae-ft-mse-840000-ema-pruned.safetensors

采样器推荐：DPM++ 2M Karras，

迭代步数推荐：30

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0.6

ADetailer开启，AD模型推荐：face_yolov8s.pt

lora权重推荐0.7

CFG为：5.5~7

CLIP推荐：2

泛化性很好可结合其他lora，希望大家多返图多点赞，谢谢