[Flux.1 D] "Honkai: Star Rail" Big Black Tower cosplay costume

触发词/Trigger word:

A photo of a slim beautiful woman in honkaistarrail-theherta cosplay costume. She is wearing see-through dress with long wide detached sleeves and choker. She is also wearing high heel knee boots and black pantyhose with thigh strap. She has very long purple hair with witch hat.

示例图片触发词/Sample images trigger words:

A photo of a slim beautiful woman in honkaistarrail-theherta cosplay costume. She is wearing see-through dress with long wide detached sleeves and choker. She is also wearing high heel knee boots and black pantyhose with thigh strap. She has very long purple hair with witch hat. She is standing on the edge of the roof with neon and led lights, behind is a futuristic cyberpunk skyline with skyscrapers. The photo is a full shot with her entire body visible and full body and with detail background.

祝大家抽卡不歪，十连出金！

LORA采用黑森林原版22g Flux模型作为底膜进行训练。使用时LORA强度可以直接设置为‘1.00’

某些效果图我使用了FaceDetailer进行脸部重绘，如果你不喜欢直出的脸，建议使用FaceDetailer进行脸部重绘

效果图我的出图流程是:

FLUX官方演示工作流直出 1152*1536 -> SD1.5脸部重绘（个人比较喜欢sd1.5的脸，您可以根据您喜好重绘）

效果图出图模型为黑森林原版22g Flux模型。出图采样器为ddim+beta，或ddim+ddim_uniform。步数为30步

诚挚邀请您尝试此LORA，作者很希望能得到您的反馈和建议。如果您能分享您生成的美图就更好了。感谢~