(FLUX.2 Klein) Evanescia | 绯英 Honkai: Star Rail 崩坏：星穹铁道

Model infov1.0 currently has the best fidelity.This LoRA is fine-tuned on a dataset of 550+ images. It can recreate character using the trigger word Evanescia 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 Anima, IllustriousXL, NoobAI, AnimagineXL, PonyXL and WAI-IllustriousXL.Param SettingsRecommended weight: 0.8 - 1.0example prompt :(Please adjust the prompts according to model card of the checkpoint you are using.)An anime illustration of Evanescia sitting on a mossy rock in a magical forest at night. She has pink ears and pink hair. She is wearing white jacket, skirt and pantyhose. She is looking at viewer with a smile. The forest is alive with bioluminescent mushrooms and floating blue light particles. There is a pond reflecting the magic lights. The atmosphere is dreamy and ethereal with cinematic lighting.TipsOfficial design is bound to the following tags: white jacket, white shirt, skirt, bow, pantyhose, boots, glovesBased on user feedback, if your checkpoint has a strong prior for Yae Sakura (Honkai 3rd) or Yae Miko (Genshin Impact), try adding yae sakura, yae miko, hair down to the negative prompt to suppress the long hair effect.If you find the official outfit elements are not decoupling when using your own checkpoint, add cloth tags to the negative prompt. For example, if you want an bare-shoulder look, add bare shoulders to the positive prompt, remove white jacket or add it to the negative prompt.OthersModels are automatically deployed via AI Agent. Please report any parameter errors or version issues in the comments.While I am very satisfied with the accuracy of her features, 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。550+ 张图片的数据集上微调得到。此LoRA使用触发词 Evanescia 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