冷门角色，素材太少，还原度不高，还望有志之士提供高清素材。

Unpopular roles, too little character material, resulting in low character similarity, but also hope that people to provide high-definition material.

我是Pixiv很有精神的森下下士，我的Pixiv个人主页：https://www.pixiv.net/users/17321274 ，你可以在这里查看我所有投稿图片的具体参数，并免费获得我的所有作品。请注意，我的作品永远不收费，从来不贩卖！

I am Pixiv 很有精神的森下下士, my Pixiv personal homepage: https://www.pixiv.net/users/17321274, you can be in here to see all specific parameters of pictures , and free access to all of my work. Please note that my work is never charged and never sold!

这是一个来自中国动漫《斗罗大陆》的角色——独孤雁。本Lora训练图集不包含任何真人图片。底模使用国风V3.3。感谢群内大佬提供的RTX 4080用于Lora训练！再次感谢！参考Lora权重0.7-0.9。

This is a character from the Chinese anime series “Douluo Dalu”（Soul Land）——Dugu Yan. This Lora training atlas does not contain any images of real people. The basic mold uses Guofeng V3.3.Thank you for the RTX 4080 provided by the warm-hearted friend in the QQ group for Lora training! Thank you again!Reference Lora weight 0.7-0.9.

参考正面tag如下——Reference Pro tag：

• 1girl,mature female,cityscape,night,looking at viewer,short hair,skirt,detached sleeves,metal trim,bare shoulders,collar,bare legs,multicolored dress,jewelry,gradient dress,short skirt,pleated skirt,scale armor,breastplate,upper body,blue skirt,

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,

版权说明：我的Lora训练均使用网络公开图片进行训练，训练后的Lora成品不推荐用于商业用途。如果你用于商业用途，一切风险由你自己承担，我不承担任何责任！

Copyright Note: My Lora training is trained using public images on the Internet, and the Lora is not recommended for commercial use. If you use for commercial purposes, all the risk is borne by you, I do not assume any responsibility!

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。你可以在我Pixiv个人主页找到我的个人联系方式。你需要提供:人物立绘、广告图、宣传图、CG渲染图、海报等类似的图片，且至少拥有清晰的正面上半身。视频截图、侧身、背身、AI绘画的图片训练效果很差，不适合用于Lora训练。

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. You can find my personal contact information on my Pixiv homepage. You need to provide: character sketches, advertising images, promotional images, CG renderings, posters, etc., with at least a clear front upper body. Video screenshots, side, back, AI painting picture training effect is poor, not suitable for Lora training.