This LoRA model is a character enhancement model for Nefer in Genshin Impact, fine-tuned on a dataset of 1000+ images(liked her so much and accidentally collected too many images.Oh Nefer please step on me).
Recommended weight: 0.7-1.0
Example prompt:
masterpiece, best quality, very aesthetic, Nefer, 1girl, solo, breasts, gloves, thigh strap, looking at viewer, jewelry, sitting, smile, hair ornament, dress, earrings,
Full body prompt:
masterpiece, best quality, very aesthetic, Nefer, 1girl, solo, breasts, gloves, thigh strap, looking at viewer, jewelry, sitting, smile, hair ornament, dress, earrings, high heels,
While I am very satisfied with the accuracy of Nefer's features, the dataset was so large that I set the batch size too small during my first fine-tuning attempt, causing the LoRA to learn excessive background information. I will release an optimized version of the model within 2 days.
In addition to the version based on Illustrious XL, I have also trained a version based on ZukiAnimeIll (a derivative model of Illustrious XL). Users employing ZukiAnimeIll for inference can use either this version or that specific one.
(Please adjust the prompts according to the official documentation of the checkpoint model you are using.)
这是一个《原神》角色Nefer 的角色增强LoRA 模型，基于1000 +图片的数据集进行微调（因为太喜欢她了，不小心收集了太多图片。 Oh，奈芙尔踩我）。
推荐权重：0.7-1.0
示例prompt:
masterpiece, best quality, very aesthetic, Nefer, 1girl, solo, breasts, gloves, thigh strap, looking at viewer, jewelry, sitting, smile, hair ornament, dress, earrings,
全身prompt:
masterpiece, best quality, very aesthetic, Nefer, 1girl, solo, breasts, gloves, thigh strap, looking at viewer, jewelry, sitting, smile, hair ornament, dress, earrings, high heels,
（提示词请根据你使用的checkpoint模型的官方文档进行调整）
尽管我对Nefer 角色特征的准确性非常满意，但数据集太大了，以至于我第一次微调时把batch size 设置得过小，导致LoRA 学进去了多余的背景信息。我会在2天之内发布优化版本的模型。
除了基于Illustrious XL 的版本，我还训练了一个基于ZukiAnimeIll（Illustrious XL 的衍生模型）的版本。使用ZukiAnimeIll 进行推理的用户既可以使用此版本，也可以使用那个专用版本。
如果有任何反馈意见欢迎评论，以便我做出调整，谢谢。