做了半天2.0结果感觉质量还不如1.0，你们对比着看吧，喜欢用哪个就用哪个。素材实在太少，而且都很模糊，2.0的人物都有点模糊，没办法。

After doing 2.0 for half a day, the quality of the result is not as good as 1.0. So just compare and see, you can use whichever you like. The material is too little, and it is very vague, 2.0 characters are a little fuzzy, there is no way.

我的Pixiv个人主页 / My Pixiv personal homepage: https://www.pixiv.net/users/17321274

这是一个来自中国动漫《斗罗大陆》的角色——水冰儿。本Lora训练图集不包含任何真人图片。参考Lora权重0.65。和国风3.3兼容性较好的模型有：ReV Animated, DreamShaper, GCM-Game Concept Map等，你可以尝试使用这些模型进行AI绘图。

This is a character from the Chinese anime series “Douluo Dalu 2”（Soul Land 2）——Shui Bing'er. This Lora training atlas does not contain any images of real people.Reference Lora weight 0.65.Models with good compatibility with Gufeng 3.3 include: ReV Animated, DreamShaper, GCM-Game Concept Map, etc. You can try to use these models for AI drawing.

Lora召唤词：DLDLshuibinger

参考正面tag如下——Reference Pro tag：

• DLDLshuibinger, 1girl, solo, blue hair, blue eyes,dress,single thighhigh,thigh strap,long sleeves,clothing cutout, capelet, gloves, looking at viewer, cityscape, night, mature female, hand on hip,

参考负面tag如下——Reference Neg tag：

• (worst quality, low quality:1.4), monochrome, zombie,undefinedEasyNegative, lowres, bad anatomy, bad hands, text, error, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry,too many fingers, thick lips, oversized head,facing away,extra arms,extra ponytail,bad eyes,fused eyes,distorted eyes,multicolored eyes,small breasts,loli,distorted background, overexposure,

如果你有喜欢的人物角色，希望将他们做成Lora，你可以联系我帮助你训练Lora模型，不收取任何费用。

If you have a favorite character that you would like to make Lora, you can contact me to help you train Lora models at no charge.

我的个人AI交流群：828795031

入群密码：S82KFCV50

群内不搞黄，不收费，不教萌新（萌新请自学），欢迎进来交流技术。