Model info

v1.0 currently has the best fidelity.

This LoRA is fine-tuned on a dataset of 200+ images. It can recreate character using the trigger word Pearl alone, while also providing detachable clothing tags.

In addition to LoRA based on Flux.2 Klein 9b & 4b, I've also trained versions based on IllustriousXL, Anima , NoobAI, AnimagineXL, PonyXL and WAI-IllustriousXL.

Param Settings

• Recommended weight: 0.8 - 1.0

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

An anime illustration of Pearl sitting on a throne in a room. She has blonde hairs and wearing dress. She is looking at viewer with a light smile. The room is composed of golden walls. The floor is reflecting lights.

Others

(Automatically deployed via AI Agent. Please report any parameteror version issues in the comments.)

While I am very satisfied with the accuracy, please feel free to leave your generations or feedback.

Thank you for your support!

模型简介

v1.0目前还原度最佳。

200+ 张图片的数据集上微调得到。此LoRA使用触发词 Pearl 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Flux.2 Klein 9b & 4b, 我还微调了 Anima, IllustriousXL, NoobAI, AnimagineXL, PonyXL 和 WAI-IllustriousXL的版本。

推荐设置

• 推荐权重： 0.8 - 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。）

• 上本身prompt:

An anime illustration of Pearl sitting on a throne in a room. She has blonde hairs and wearing dress. She is looking at viewer with a light smile. The room is composed of golden walls. The floor is reflecting lights.

小记

（模型由AI Agent全自动发布，若参数、模型版本有问题，欢迎评论反馈）

虽然我已经对她的特征还原程度很满意，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