欢迎使用MIAOKA_Anime Girl模型 这个模型 是类二次元风格的人物模型 及 MiaoKa_reality 转变画风模型
Welcome to use the miaoka_anime girl model which is a secondary model of the class and the transformation of the miaoka_reality model
------------------------------------------------------------------------------------------
这个模型为了是适配 MiaoKa_reality Checkpoint模型 模型的微调模型
这个模型可以实现让MiaoKa_reality 转变画风为二次元画风
当然这个微调模型可以可单独使用搭配其他 Checkpoint模型来使用
This model is a fine-tuned model of the MiaoKa_reality Checkpoint model
This model allows miaoka_reality to change the style of drawing to animation
Of course, this fine-tuning model can be used separately from other Checkpoint models
画风转变方法：
如需要在使用MiaoKa_reality Checkpoint模型时候把画风转变成二次元画风 择需要加入 A模型： <lora:MIAOKA_Anime Girl:1> + B模型：例如： <lora:MIAOKA_Meidusha_v1.0:1> 即可将画风转变成二次元画风
If you need to change the painting style into quadratic painting style when using MiaoKa_reality Checkpoint model, you need to add model A: <lora:MIAOKA_Anime Girl:1> + B model: for example:<lora:MIAOKA_Meidusha_v1.0:1> The painting style can be transformed into a secondary painting style
---画风转换前⬆ （before）---------------------- 画风转换后⬆（after)---
使用建议（ Recommendations of use）:
此模型是基于MiaoKa_reality训练而成 建议搭配 MiaoKa_realityCheckpoint模型来使用
This model is based on MiaoKa_reality training. It is recommended to use it with MiaoKa_realityCheckpoint model
------------------------------------------------------------------------------------------
推荐的参数（Recommended parameters）:
采样方法（Sampler:）:
Euler a: 20~30步。
DPM++ SDE Karras:20~30步。
DPM++ 2M SDE Karras20~40步。
提示词引导系数(CFG Scale):7
人像人物分辨率（Character resolution）：512x768, 768x768，512x1024
背景图风景图分辨率（Background and landscape resolution）: 768x512, 1024x512, 1536x512
高清修复（Hires.fix）：
放大算法:R-ESRGAN 4x+Anime6b 4x-UltraSharp，
高分迭代步数：10~15
重绘幅度：0.3~ 0.5
Clip Skip:2。
负面（Negatives):推荐用嵌入式embeddings模型中的 EasyNegative,或组合 (worst quality, low quality:1.4), monochrome, zombie, (interlocked fingers:1.2), 一起使用
------------------------------------------------------------------------------------------
模型反馈请站内私信
图像源和训练代码来自互联网，模型仅用于科研兴趣交流。如有侵权，请联系删除，谢谢。
The image source and training code are from the Internet, and the model is only used for scientific interest exchange. If there is infringement, please contact to delete, thank you.