Model ideas come from War Royale, Brawl and other Q edition illustrations
Bottom mold recommendation: The whole net first | SHMILY classical colorful _v1.0,
Sampler recommended: DPM++ 2M Karras,
Recommended number of iteration steps: 30
It is recommended to open the HD repair: the magnification algorithm is R-ESRGAN 4x+ Anime6B, magnify 2 times, and the redraw amplitude is 0.3
ADetailer is enabled. Recommended AD model: face_yolov8n.pt
The recommended weight for lora is 0.4-0.65
CFG: 5.5
CLIP Recommended: 2
VAE recommendation: vae- FT-MSE-84000-EMA-Pruned.safetensors
The generalization is very good and can be combined with other lora, I hope you can return more pictures and praise more, thankyou
模型创意来于皇室战争，荒野乱斗等Q版插画
底模推荐：全网首发｜SHMILY古典炫彩_v1.0，
采样器推荐：DPM++ 2MKarras，
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0.3
ADetailer开启，AD模型推荐：face_yolov8n.pt
lora权重推荐0.4-0.65
CFG为：5.5
CLIP推荐：2
VAE推荐：vae-ft-mse-840000-ema-pruned.safetensors
泛化性很好可结合其他lora，希望大家多返图多点赞，谢谢
