刚学炼丹的时候炼着的。。。但是dataset找不到了，等再找份素材重新训一下吧，其实感觉这个之前训的也还行，没测试泛化性。

THIS LORA IS ONLY FOR TEST, PLEASE DO NOT PUBLISH NSFW IMAGES TO THE COMMUNITY!!!

The weight of Lora = 0.8-0.9, strongly suggest is 9.

Please heighten your steps to 40 more or less to generate good images.

________________

V1.2

used chill remix as pretrained model, used new dataset,

just a try.

Over here, I really wanna taunt some loras which were trained strongly overfitting.

How dare u published to Cvitai!