Krea2版本强烈建议使用自然语言。

The Krea2 version strongly recommends using natural language.

免责声明

本 LoRA 为《王者荣耀》相关角色/皮肤的同人模型，仅供个人学习、研究、交流与非商业同人创作使用。相关角色与美术形象的版权归原版权方所有。本人不拥有相关版权，本 LoRA 亦非官方内容，未获得官方授权。禁止将本 LoRA 或使用本 LoRA 生成的内容用于任何商业用途。

这是一个《王者荣耀》貂蝉皮肤「貂蝉 · 馥梦繁花（Alphonse Mucha Collaboration）」的角色 LoRA。
请注意：这是一个双形态角色 LoRA。
繁花形态触发词：
Diaochan_FMFH_FANHUA
馥梦形态触发词：
Diaochan_FMFH_FUMENG
如果想生成双形态同框，可以同时使用两个触发词：
Diaochan_FMFH_FANHUA, Diaochan_FMFH_FUMENG, 2girls, multiple_girls
推荐搭配提示词：
繁花形态：
white dress, bare shoulders, flower, butterfly, petals, garden, warm sunlight, floral atmosphere, elegant goddess pose
馥梦形态：
blue and black dress, bare shoulders, moonlit atmosphere, reflective water, crystal ornaments, glowing lanterns, cool blue lighting, dreamy nocturnal atmosphere
Krea2:
推荐 LoRA 强度：0.95
Recommended LoRA weight: 0.95
推荐步数：8-10

Recommended sampling steps: 8–10
推荐 CFG：1
Recommended CFG scale: 1.1
推荐采样器: er_sde，Euler A
Recommended samplers: er_sde, Euler A
Anima:
推荐 LoRA 强度：1

Recommended LoRA strength: 1
推荐步数：30

Recommended steps: 30
推荐 CFG：5

Recommended CFG: 5
推荐采样器：er_sde, Euler A
Recommended samplers: er_sde, Euler A
这是一个偏角色还原向的 LoRA，两个形态分别通过不同触发词控制。生成单独形态时，请使用对应触发词；如果需要双人同框或形态对照效果，可以同时使用两个触发词。
由于训练数据和基础模型表现限制，服装细节、面部细节以及双形态同框的稳定性可能无法每次都完全还原。建议根据使用的底模、分辨率、LoRA 权重和提示词强度进行适当调整。
如果在使用过程中遇到问题，欢迎反馈。感谢大家的支持。
This is a character LoRA for Diaochan’s skin “Diaochan · Fragrant Dream Blossom (Alphonse Mucha Collaboration)” from Honor of Kings.

Please note: this is a dual-form character LoRA.

Form 1: Fragrant Blossom / Fan Hua

Trigger word:

Diaochan_FMFH_FANHUA

Form 2: Fragrant Dream / Fu Meng

Trigger word:

Diaochan_FMFH_FUMENG

For dual-form images, you can use both trigger words together:

Diaochan_FMFH_FANHUA, Diaochan_FMFH_FUMENG, 2girls, multiple_girls

Recommended optional prompt tags:

Fan Hua form:

white dress, bare shoulders, flower, butterfly, petals, garden, elegant goddess pose, warm sunlight, floral atmosphere

Fu Meng form:

blue and black dress, bare shoulders, moonlit atmosphere, reflective water, crystal ornaments, glowing lanterns, cool blue lighting, dreamy nocturnal atmosphere

This LoRA was trained as a character LoRA. The two forms are separated by different trigger words, so please use the correct trigger word depending on which form you want to generate.

Due to limitations in the training dataset and base model behavior, some costume details, facial details, or dual-form compositions may not always be perfectly reproduced. For better results, please adjust LoRA weight, prompt strength, and image resolution according to your model.

If you encounter any issues while using this LoRA, feel free to leave feedback. Thank you very much for your support.