Model info

v1.0 currently has the best fidelity.

Created this on a whim because the other Rossi LoRAs on Civitai have terrible outfit accuracy... I might be optimizing the outfit-swapping functionality in a few days.

This LoRA is fine-tuned on a dataset of 200+ images. It can recreate character using the trigger word Rossi alone. However, the one trained on standard Illustrious XL is the most stable choice to avoid feature conflicts.↓↓↓

https://civarchive.com/models/2436487

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

Param 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, Rossi, 1girl, solo, smile, blush, looking at viewer, closed mouth, upper body, black gloves, simple background,

For full-body shots, you can try adding full body or boots.

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。

因为C站内其他的洛茜LoRA的服装还原度都太糟糕，一时兴起做的，至于换装功能过几天再优化。

200+ 张图片的数据集上微调得到。此LoRA使用触发词 Rossi 即可还原人物。不过基于标准IllustriousXL训练的版本肯定是最稳妥的选择，因为不会有特征冲突。↓↓↓

https://civarchive.com/models/2436487

除了IllustriousXL, 我还微调了 Anima, Flux Klein 9b & 4b, 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。）

• 上本身prompt:

masterpiece, best quality, very aesthetic, newest, hires, Rossi, 1girl, solo, smile, blush, looking at viewer, closed mouth, upper body, black gloves, simple background,

全身可尝试添加full body, boots 等。

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