模型介绍：

这是一个生成欧美风格的幻想二次元游戏立绘Lora！

具体食用方法请看例图！！

推荐参数：

大模型：hello2danime_V20

VAE：自动

CLIP跳过：1

推荐正面tag：Concept art,

推荐负面tag：logo,text,badhandv4,EasyNegative,ng_deepnegative_v1_75t,bad_prompt Negative Embedding_v2.0,坏图修复veryBadImageNegative_veryBadImageNegative_v1.3,negative_hand-neg,poorly drawn face,extra limb,missing limb,disconnected limbs,malformed hands,ugly,

触发词：omei

Lora权重：0.8左右

迭代步数：32

采样推荐：Euler a

分辨率：768*1024

生成时遇到好看的，需要用高分辨率修复！放大算法选择R-ESRGAN 4x+，重绘幅度0.32！

最后：

需要抽卡，祝大家玩的开心，欢迎来测试和返图！！

Model Introduction:

This is a fantasy of European and American style created by the anime game Lora!

Please refer to the example picture for specific consumption methods!!

Recommended parameters:

Large model: hello2danime_V20

VAE: Automatic

CLIP skip: 1

Recommended positive tag: Concept art,

Recommended negative tags: logo, text, badhandv4, EasyNegative, ng_deepnegative_v1_75t, bad_prompt Negative Embedding_v2.0, bad image repair veryBadImageNegative_veryBadImageNegative_v1.3, negative hand neg, poor drawn face, extra limb, missing limb, disconnected limbs, malformed hands, ugly,

Trigger word: omei

Lora weight: around 0.8

Iteration steps: 32

Sampling recommendation: Euler a

Resolution: 768 * 1024

Encountered a good-looking one during generation, requires high-resolution repair! Enlarge the algorithm by selecting R-ESRGAN 4x+and redraw with an amplitude of 0.32!

Finally:

Need to draw cards, wish everyone a happy time, welcome to test and return pictures!!