This model is LOL to skin training, can produce high saturation, high quality beauty propaganda images
Bottom mold recommendation: The whole net first | SHMILY classical colorful _v1.0,
Sampler recommendation: DPM++ 3M SDE Exponential
Recommended number of iteration steps: 30
It is recommended to open HD repair: the amplification algorithm is 4x-UltraSharp,
ADetailer is enabled. Recommended AD model: face_yolov8n.pt
The recommended weight for lora is 0.5-0.75
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, thank you
This model is only used for communication and learning, and is not commercially available. It is open to download on various platforms. If it is integrated, please mark the original model to avoid unnecessary trouble.
此模型是LOL至臻皮肤训练而成，可以出高饱和度，高质量的美宣图像
底模推荐：全网首发｜SHMILY古典炫彩_v1.0，
采样器推荐：DPM++ 3M SDE Exponential
迭代步数推荐：30
推荐开启高清修复：放大算法为4x-UltraSharp，
ADetailer开启，AD模型推荐：face_yolov8n.pt
lora权重推荐0.5-0.75
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
此模型仅用作交流和学习，不可商用，在各个平台开放下载，如果融合请标注原模型以免不必要的麻烦。