众里寻他千百度。蓦然回首，那人却在，灯火阑珊处。
———宋辛弃疾
大家好，我是chosen鲷，这次带来的是灯火阑珊lora模型，使用了很多nai4图片训练，以达到这种强烈光影的效果，非常适合绘制夜间的肖像插图，意境很美。
V2版本增强了风格性，比原来光影更加强烈了。
这个lora兼容性很好，跟各种其他的lora也能在一起使用，形成那种闪闪发亮的效果，不过手有一定的崩坏概率，需要一定程度的抽卡，不过崩坏的概率倒不是很高就是了。如果有机会我可能还会重新训练更稳定的版本，等以后再说吧，权重0.5-0.8均可，光辉系模型基本都能用，例图是我用我那个chosen-mix_XLV3出的，用noob系的模型或者wai也可以获得很好的效果（下方推荐）
触发词nai4 shiny style
质量词建议加上：rim light,Volumetric Lighting,backlighting,
具体的tag可以看我例图。
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 谢谢。
The following content is from machine translation
Hello everyone, I'm chosen鲷. This time, I'm bringing you the "Volumetric Lighting" LoRA model. It was trained using many NAI4-style images to achieve this intense light and shadow effect, making it particularly suitable for creating nighttime portrait illustrations with a beautiful, poetic atmosphere.
The V2 version enhances the stylistic qualities, with even stronger light and shadow effects than before.
This LoRA has great compatibility and can be used alongside various other LoRAs to create a sparkling, shimmering effect. However, there is a certain probability of hand distortions, so some degree of "gacha" (random generation attempts) may be needed—though the chance of distortion isn’t extremely high. If I get the opportunity, I may retrain a more stable version in the future, but that’s a topic for another time. A weight of 0.5-0.8 works well, and it’s compatible with most Glorious-series models. The sample images were generated using my chosen-mix_XLV3, but Noob-series models or WAI can also produce great results (recommendations below).
Trigger word:nai4 shiny style
Recommended quality tags:rim light, Volumetric Lighting, backlighting
For specific tags, please refer to my sample images.
Thank you for downloading and using this model! If you like it, feel free to follow me. My Bilibili and Pixiv IDs are both chosen鲷. You're welcome to check out my channels:
🔗
🔗
Thanks again!
The following content is from machine translation.