V4版本更新：

• 扩充了数据集，加入部分换装和nsfw图像，加强了模型换装和脱衣的能力

• 因为在炼制V2时，有两个表现优异但侧重不同的产物，难以舍弃，就通过SuperMerger进行了合并，于是命名为V4（2+2=4）

• 最终效果既还原角色风格，也足够还原服装细节

使用方法：

• 推荐权重1.0~0.8，推荐使用高清修复，但不开启效果依然良好，不会有色块噪点

• 触发词：1girl, official, purple eyes

translate by GPT：

V4 Update:

• Expanded dataset to include some costume change and NSFW images, enhancing model's ability to change outfits and remove clothing

• During the refining process of V2, there were two products that performed exceptionally well but had different focuses, making it difficult to choose between them. As a result, they were merged using SuperMerger and named V4 (2+2=4).

• The final result not only captures the character's style but also the details of their clothing.

Instructions for use:

• Recommended weight is 1.0 to 0.8 and suggest using high-definition restoration, though it still performs well without it and won't have color block noise.

• Trigger words: 1girl, official, purple eyes

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

以下为V1说明：

基于NAI训练的星穹铁道角色——卡芙卡的模型

使用方法：

推荐权重0.7~0.9，推荐使用block weight与高清修复

核心触发词为：1girl, official, purple eyes

建议使用触发词：1girl, official, purple eyes, (empty eyes:1.2), eyewear on head, black jacket, jacket on shoulders, shirt, shorts, pantyhose, boots

translate by GPT：
Based on NAI training, the model of the Honkai Star Rail character, Kafka.

Usage:

Recommended weight is 0.7-0.9, and it is recommended to use block weight and high-definition restoration.

The core trigger words are: 1girl, official, purple eyes

It is recommended to use trigger words: 1girl, official, purple eyes, (empty eyes:1.2), eyewear on head, black jacket, jacket on shoulders, shirt, shorts, pantyhose, boots