Model info

Fine-tuned on Anima-Preview.

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

Param Settings

• Recommended weight: 0.8 - 1.0

• example prompt :

masterpiece, best quality, score_7, safe, anime, Sparxie, 1girl, v, breasts, portal, looking at viewer, open mouth, smile, dress, cleavage, boots, legs, stuffed toy, full body. She's making a peace sign with her hand, exuding a playful and cheerful demeanor. The scene suggests a lively and animated moment.

Usage Tips

• Clothing & Accessories: Sparxie's official outfit is detachable. Her official design is primarily bound to the following tags: hat, dress, choker, gloves, boots, earrings.

• Changing Outfits: In my testing with common checkpoint models, removing the official clothing tags allowed for adding any preferred clothing elements. If residual elements persist when using your specific checkpoint for inference, consider adding the aforementioned tags to the negative prompt.

Others

While I am satisfied with the fidelity of features like her mini hat, earrings...please feel free to leave your generations or feedback.

Thank you for your support!

模型信息

该模型在Anima-Preview基础上，300+ 张图片的数据集微调得到。此LoRA仅使用触发词 Sparxie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。

参数设置

• 推荐权重： 0.8 - 1.0

• 示例prompt:

masterpiece, best quality, score_7, safe, anime, Sparxie, 1girl, v, breasts, portal, looking at viewer, open mouth, smile, dress, cleavage, boots, legs, stuffed toy, full body. She's making a peace sign with her hand, exuding a playful and cheerful demeanor. The scene suggests a lively and animated moment.

使用建议

• 服装与配饰 ： 针对服装 hard-baked问题进行了专门优化。现在官方外设是可拆卸的，官方服设主要绑定在绑定了以下标签：hat, dress, choker, gloves, boots, earrings。

• 更换服装： 实测下来我在我常用的checkpoint模型上在去掉上述官方服装提示词后，可以自由添加任意喜欢的服装元素。如果你在使用其他checkpoint模型推理时仍发现有官方服装残留，建议将上述标签加入到负面提示词中。

小记

虽然我已经对火花的特征还原程度很满意，包括小礼帽、耳饰等等，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