该模型可以与使用Animagine 3.0 XL 一样使用它，我只是调节了它的一些基本画风，使其符合我的审美。

This model can be used just like using Animagine 3.0 XL, I just adjusted some of its basic art styles to fit my aesthetics.

Recommended size: 832*1216\1216*1216\others

For higher quality outcomes, prepend prompts with:

为了获得更高质量的结果，请在提示前添加以下内容：

masterpiece, best quality

This follows:

遵循这样生图：

1girl/1boy, character name, series, everything else in any order.

To guide the model towards generating high-aesthetic images, use negative prompts like:

请使用负面提示，例如：

nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name

这只是我第一次尝试，也是基于兴趣的尝试。

This is just my first attempt, and it is also an attempt based on interest.

欢迎您的使用和返图。

Welcome to use and return pictures.

If publishing troubles you, please contact me to deal with it.

有时，我不想要太淡的画风，这对我没有吸引力。

Sometimes I don’t want a painting style that’s too bland

我喜欢Animagine 3.0，下称A3，但想改变它的基础画风。

I like Animagine 3.0, hereafter referred to as A3, but I want to change its basic painting style.

一次尝试，我改变了一些基础画风，您可以像A3一样使用它。

As a try, I changed some basic painting styles and you can use it like A3.

我的目的是微调A3的画风，使其靠近我想要的风格。

My goal is to fine-tune the painting style of A3 to make it closer to the style I want.

由统一风格的nai3风格图片约12k，即是一种亮+新的风格微调画风。

size：832*1216/1216*1216

The nai3 style pictures are about 12k in a unified style, which is a bright + new style fine-tuned painting style.

当我折腾了几天后，我并不想它画风过于鲜艳以至于影响解构的合理性。

After tinkering with it for a few days, I didn’t want it to be too bright and affect the rationality of the deconstruction.

由A3 base ft 10epo+25epo，并由输出模型为基模训练lora10epo，lora再与模型合并。

10epo+25epo ft from A3 base, and lora10epo is trained from the output model as the base model, and lora is then merged with the model.