Model Description

v1.1 has the highest fidelity.

This LoRA is fine-tuned on a dataset of 300+ images. It can recreate Yvonne (Arknights: Endfield) using the trigger word Yvonne alone, while also providing detachable clothing tags for creative flexibility.

In addition to LoRA based on Illustrious XL, I have also trained versions based on NoobAI, AnimagineXL, PonyXL, WAI-IllustriousXL, and ZukiAnimeIll. Comming soon.

Param Settings

• Recommended weight: 0.9 - 1.0

• example prompt :(Please adjust the prompts according to model card of the checkpoint you are using.)

masterpiece, best quality, amazing quality, 1girl, solo, looking at viewer, jacket, upper body, breasts, smile, cute, playful, simple background, detailed light, 

• full body:

masterpiece, best quality, amazing quality, 1girl, solo, looking at viewer, jacket, gloves, breasts, pants, boots, tail, smile, cute, playful, simple background, detailed light, 

For full-body shots, you can try adding full body and tail.

Tips

• Official design is bound to the following tags: jacket, gloves, pants, boots, tail.

• If you do not want the tail, add tail to the negative prompt.

• If you find the official outfit elements are not decoupling when using your own checkpoint, lower model weight or add jacket, gloves, pants, boots or Yvonneto the negative prompt.

Others

While I am satisfied with the fidelity of features like her asymmetrical bra or peculiar tail...please feel free to leave your generations or feedback.

Thank you for your support!

模型简介

v1.1 具有最高的还原度。

这个LoRA模型是角色伊冯（明日方舟：终末地）的角色增强模型，在300+ 张图片的数据集微调得到。此LoRA使用触发词Yvonne即可还原人物，也提供了可拆卸的服装提示词，方便各类二创发挥。

除了基于Illustrious XL的版本，我还训练了基于NoobAI，AnimagineXL，PonyXL，WAI-IllustriousXL，ZukiAnimeIll的版本，coming soon 。

参数设置

• 推荐权重： 0.9 - 1.0

• （请根据你实际使用的Checkpoint模型的官方文档，适当调整提示词策略。）

• 示例prompt:

masterpiece, best quality, amazing quality, 1girl, solo, looking at viewer, jacket, upper body, breasts, smile, cute, playful, simple background, detailed light, 

• 全身:

masterpiece, best quality, amazing quality, 1girl, solo, looking at viewer, jacket, gloves, breasts, pants, boots, tail, smile, cute, playful, simple background, detailed light, 

全身可尝试添加full body, tail 等。

Tips

• 官方服设绑定在以下标签：jacket, gloves, pants, boots, tail。

• 如果你不想要尾巴，在负面提示词加 tail。

• 如果你在使用底模进行换装时，发现服装元素不能完全解耦，请在负面提示词加入 jacket, gloves, pants, boots或Yvonne。

小记

虽然我已经对伊冯的特征还原程度很满意，包括不对称的胸衣，独特的尾巴等等，但如果有任何反馈意见欢迎评论，以便我做出调整，谢谢。我会定期在社交媒体发布图片，可在对应平台取原图。

Bilibili账号：https://space.bilibili.com/12595237?spm_id_from=333.1007.0.0

小红书账号：