LoRA model of Futaba Kayano (茅野ふたば) from media-mix project Denonbu (電音部).
The trigger word is futaba kayano (denonbu). I think the overall result is good with LoRA weights 0.75-0.8. However, you can try other weights.
Note: I load my LoRA model through the additional network WebUI plugin, so the prompt of sample illustrations don't contain <lora:XXX:X> tag. Due to the limited training set, the model has the problem of overfitting (including over-changing the style of base model, difficulty to changing positions, and pollution of clothing style).
I'll appreciate it if you're willing to use this LoRA model and share AI arts to other people. My models and illustrations are free for everyone, and if you like them, please support me at Patreon or 爱发电.
————————————
跨媒体企划《电音部》的角色茅野双叶(暂译)的LoRA模型
模型的触发词为futaba kayano (denonbu)。设置LoRA权重为0.75-0.8时有不错的效果,不过您也可以尝试其他权重值
我使用的是WebUI的可选附加网络(additional network)插件,所以示例图的prompt里并没有<lora:XXX:X>的tag,还请注意。由于训练集很小,该模型有过拟合的问题(包括过度改变基底模型风格、难以改变姿态以及服装样式污染)
如果您愿意使用本LoRA模型并将作品分享给其他人,本人将不胜感激。本人制作的所有模型和绘画皆免费提供,如果觉得还不错的话,欢迎在Patreon或爱发电上支持我,非常感谢。