Model info

Fine-tuned on Anima-Preview.

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

Param Settings

• Recommended weight: 0.7 - 1.0

• example prompt :

masterpiece, best quality, score_7, safe, 1girl, solo, looking at viewer, jacket, smile, standing, cowboy shot, cute, playful, detailed light, holding a rectangular sign out in front of her that reads "Yvonne in Anima".

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

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

As this is a fresh release, I am currently experimenting with new parameter ratios to find the optimal balance.

Thank you for your support!

模型信息

该模型在Anima-Preview基础上，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。

推荐设置

• 推荐权重： 0.7 - 1.0

• 示例prompt:

masterpiece, best quality, score_7, safe, 1girl, solo, looking at viewer, jacket, smile, standing, cowboy shot, cute, playful, detailed light, holding a rectangular sign out in front of her that reads "Yvonne in Anima".

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

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

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：