大家好，我是chosen鲷，这次给大家带来的事碧蓝航线人物lora。

训练这个lora的原因是我发现anima大模型对很多碧蓝人物不能有效识别或出图效果不好，最典型的就是约克城Ⅱ和列克星敦Ⅱ，偏偏这两位还是我非常喜欢的角色，所以我决定训练一系列的人物lora去解决这个问题，但是每训练一个都单发一个模型也忒麻烦了，所以我决定搞一个发布页面，然后后续训练的所有角色都扔这一个模型页面，大家按需下载即可。

支持的人物：

约克城Ⅱ触发词：lexington ii \(azur lane\)

列克星敦Ⅱ触发词：Lexington ii \(azur lane\)

。。。

后续再有新的人物一律在这里补充。

推荐的质量tag：masterpiece, score 7, score 8, highres, absurdres, best quality, explicit, safe, sfw, detail eyes, multicolored_background, multicolored eyes, @yoshida_akihiko, @satsuya, @atdan:0.5, @dsmile, @yolanda, @rella, @ciloranko,

生成参数：cfg1 step12（使用加速lora的情况下）cfg4 step50（不使用加速lora的情况下），euler+simple,降噪 0.95,尺寸建议直接出1920*1080。

大模型首推我的鸢尾花和chosen-mix_anima（下方推荐）,miaomiao1.4和一些其他的anima模型也可以。

感谢大家的下载使用，如果喜欢的话欢迎关注我，我的bilibili pixiv ID均为chosen鲷，欢迎大家关注我的频道https://space.bilibili.com/3867754?spm_id_from=333.337.0.0 https://www.pixiv.net/users/102907778 谢谢。

The following content is from machine translation

Hello everyone, I'm Chosen Snapper. Today I'm bringing you a character LoRA for Azur Lane.

The reason I trained this LoRA is that I found the Anima base model often fails to recognize many Azur Lane characters effectively or produces poor results—the most typical examples being Yorktown II and Lexington II. Unfortunately, these two happen to be characters I really like, so I decided to train a series of character LoRAs to solve this issue. However, releasing a separate model for each one would be way too troublesome, so I decided to set up a single release page. All future characters I train will be uploaded to this same model page, and you can download whichever ones you need.

Supported characters:

Yorktown II — Trigger word: yorktown ii \(azur lane\)

Lexington II — Trigger word: lexington ii \(azur lane\)

...

Any new characters added later will be supplemented here.

Recommended quality tags:

masterpiece, score 7, score 8, highres, absurdres, best quality, explicit, safe, sfw, detail eyes, multicolored_background, multicolored eyes, @yoshida_akihiko, @satsuya, @atdan:0.5, @dsmile, @yolanda, @rella, @ciloranko

Generation parameters:

CFG 1, step 12 (when using the acceleration LoRA)

CFG 4, step 50 (when not using the acceleration LoRA)

Euler + Simple, denoising 0.95

Recommended resolution: go straight to 1920×1080.

For the base model, I highly recommend my Chosen-irises_anima and Chosen-Mix_Anima (see below for recommendations). Miaomiao 1.4 and some other Anima models also work well.

Thank you for downloading and using my work. If you like it, feel free to follow me. My Bilibili and Pixiv IDs are both "Chosen Snapper". Welcome to follow my channels:

https://space.bilibili.com/3867754?spm_id_from=333.337.0.0

https://www.pixiv.net/users/102907778

Thanks!