Model Description

v1.0 currently has the highest fidelity.

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

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

Recommended Settings

• Recommended weight: 0.8 - 1.0

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

masterpiece, best quality, very aesthetic, newest, hires, Tangtang, 1girl, solo, eyepatch, jacket, gloves, looking at viewer, smile, :d, open mouth, cowboy shot, claw pose, hands up, youthful, lively, detailed light, simple background, depth of field, blurry background,

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

Tips

• Official design is bound to the following tags: jacket, shirt, jewelry, gloves, black shorts, black socks, shoes.

• If you do not want the eyepatch, add eyepatch 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, jewelry, necklace, gloves, shirt, shorts, shoes, tassel, earrings, to the negative prompt.

Others

Models are automatically deployed via AI Agent. Please report any parameter errors or version issues in the comments.

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

Thank you for your support!

模型简介

v1.0 目前有最高的还原度。

这个LoRA模型是角色汤汤的角色增强模型，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NoobAI, 我还微调了 Anima, Flux Klein 9b & 4b, IllustriousXL, 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。）

• 示例prompt:

masterpiece, best quality, very aesthetic, newest, hires, Tangtang, 1girl, solo, eyepatch, jacket, gloves, looking at viewer, smile, :d, open mouth, cowboy shot, claw pose, hands up, youthful, lively, detailed light, simple background, depth of field, blurry background,

全身可尝试添加full body, boots 等。

Tips

• 默认服装元素绑定在以下关键词: jacket, shirt, jewelry, gloves, black shorts, black socks, shoes。

• 如果你不想要眼罩，把 eyepatch 放到负面提示词。

• 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，请降低模型权重或在负面提示词酌情加入 jacket, jewelry, necklace, gloves, shirt, shorts, shoes, tassel, earrings, 。

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。

虽然我已经对特征还原程度很满意，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