Model Description
Note: Personally, the WAI-IllustriousXL v15 official checkpoint model is far more stable in terms of output quality compared to v16.
This LoRA model is a character enhancement model for Nefer from 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). The base-model is WAI-IllustriousXL (v16&v15), please download and use together (remember to select the corresponding LoRA version).
Usage Tips
Special optimization has been applied to address the hard-baked clothing issue. Nefer's official accessories and outfit elements are now more flexible: her primary clothing is bound to "dress", "gloves", and "thigh strap", while her accessories are linked to "hair ornament", "jewelry", and "earrings". Her footwear is bound to "high heels".
Omitting these clothing tags will default to her official illustration appearance. During testing with my usual Illustrious series checkpoint models, removing these tags allows for adding preferred alternative outfits. If residual elements persist when using your specific checkpoint for inference, consider adding the aforementioned phrases to the negative prompt.
Recommended Settings
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,
Others
I am extremely dedicated to capturing Nefer's aesthetic, and with over 1000 images in the dataset, the character's fidelity is highly consistent.
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.)
If you have any feedback, please feel free to leave comments so I can make adjustments. Thank you.
Bilibili账号： https://space.bilibili.com/12595237?spm_id_from=333.1007.0.0
小红书账号：
模型简介
注：个人感觉 WAI-IllustriousXL官方checkpoint模型v15比v16出品要稳定许多。
这个LoRA模型是《原神》角色 奈芙尔 (Nefer) 的角色增强模型，在 1000+ 图片的数据集上微调的。底模是 WAI-IllustriousXL (v16&v15)，请搭配使用（注意选择对应的lora型号）。
使用建议
这次特意对角色服装hard-baked问题进行了优化，现在奈芙尔的官方外设是可拆卸的。她的裙装主要绑定在 "dress"，手套和腿带分别绑定在 "gloves" 和 "thigh strap"，饰品绑定在 "hair ornament", "jewelry", "earrings"，鞋子则绑定在 "high heels"。
不加服装提示词就会默认呈现官方立绘造型。如果你在使用你的checkpoint模型推理时仍有残留，可以考虑在负面提示词一栏加入上述短语。
推荐设置
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,
小记
由于我对奈芙尔这个角色的喜爱，这次使用了超过1000张的高质量素材进行训练，以确保对她细节特征的精准还原。
除了基于Illustrious XL的版本，我还训练了基于 ZukiAnimeIll（Illustrious XL的一款衍生模型）的版本，使用ZukiAnimeIll推理的用户可以使用该版，也可以使用那一版。
（提示词请根据你使用的checkpoint模型的官方文档进行调整）
如果有任何反馈意见欢迎评论，以便我做出调整，谢谢。