大家好，我是chosen鲷，这次带来的是天城しの风格的OL lora。
训练集主要来自于画师天城しの的OL小姐姐图，源自天城老师经常画一个OL角色，非常的俏皮可爱，我一直非常喜欢。这位画师的风格也很有特点，他基本上都是在用软变喷枪笔刷在作画，所有的明暗交界线都是柔和的，和现在比较常见的，用大色块去掐明暗交界线的厚涂画法背道而驰，有一种早期gal的感觉，配色上多以明亮为主，对于高光的使用非常不吝啬，这也导致画面看起来稍微有一点点腻，不过我个人而言还是很喜欢这种感觉的。
lora兼容性不错，建议权重0.9，可以作为风格挂架去搭配其他人物lora使用。触发词：Shino amagi OL
推荐的tag：
Shino amagi OL
这里写你想要的内容
<lora:Shino amagi OL-000018:0.9>,
Negative prompt: EasyNegative,badhandsv5-neg,Subtitles,word,
Steps: 32, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 1168584198, Size: 512×768, Model hash: 52b8ebbd5b, Model: chosen-mix bake vae, Denoising strength: 0.5, Clip skip: 2, Hires upscale: 2, Hires steps: 12, Hires upscaler: R-ESRGAN 4x+, Lora hashes: “Shino amagi OL-000018: 0a79c3067456”, TI hashes: “EasyNegative: 66a7279a88dd, badhandsv5-neg: aa7651be154c”, Version: v1.6.0-2-g4afaaf8a
大模型我推荐用我的chosen mix或者chosen impasto（就是下方推荐里第一个），其他的常见模型诸如ghost一类的也都可以，这模型的兼容性还不错，推荐使用兼容性好的二次元大模型.
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=333.1007.0.0，https://www.pixiv.net/users/40911695 谢谢。
The following content is from Google Translate
Hello everyone, I am chosen鲷, and this time I bring you an OL lora in the style of Shino Amagi.
The training set mainly comes from illustrations of an OL character by the artist Shino Amagi. This artist often draws an adorable and playful OL character that I really like. The artist’s style is also quite distinctive, using soft variable spray gun brushes for painting. The boundaries between light and shadow are all soft, contrasting with the common thick paint technique that uses large color blocks to define the boundaries. It gives a feeling reminiscent of early gal art, with bright colors and generous use of highlights. This sometimes makes the artwork appear slightly saturated, but personally, I really enjoy this feeling.
Lora has good compatibility, and I recommend setting the weight to 0.9. It can be used as a style reference to complement other character loras. Trigger word: Shino Amagi OL
Recommended tags:
Shino Amagi OL Write desired content here <lora:Shino Amagi OL-000018:0.9>,
Negative prompt: EasyNegative, badhandsv5-neg, Subtitles, word, Steps: 32, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 1168584198, Size: 512×768, Model hash: 52b8ebbd5b, Model: chosen-mix bake vae, Denoising strength: 0.5, Clip skip: 2, Hires upscale: 2, Hires steps: 12, Hires upscaler: R-ESRGAN 4x+, Lora hashes: “Shino Amagi OL-000018: 0a79c3067456”, TI hashes: “EasyNegative: 66a7279a88dd, badhandsv5-neg: aa7651be154c”, Version: v1.6.0-2-g4afaaf8a
For the large model, I recommend using my chosen mix or chosen impasto (the first one recommended below). Other common models like ghost can also be used, as they are compatible with this style. This model has good compatibility and is recommended for use with high-quality anime-style large models.
Thank you all for downloading and using it. If you like it, please follow me. My bilibili and pixiv IDs are both chosen鲷. You are welcome to follow my channels: https://space.bilibili.com/3867754?spm_id_from=333.1007.0.0, https://www.pixiv.net/users/40911695 Thank you.