触发词/Trigger words:

A photo of a tall and slim beautiful woman in zenlesszonezero-qingyi cosplay costume, include cropped shirt and blue vest and choker and belt, and detached sleeves with arm armor and fingerless gloves, and blue short shorts, and knee pads and leg armor and cosplay shoes. She has long dark green twintails hair with hair ribbon and hair ball.

示例图片触发词/Trigger words of sample images:

A photo of a tall and slim beautiful woman in zenlesszonezero-qingyi cosplay costume, include cropped shirt and blue vest and choker and belt, and detached sleeves with arm armor and fingerless gloves, and blue short shorts, and knee pads and leg armor and cosplay shoes. She has long dark green twintails hair with hair ribbon and hair ball. 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 body shot with her entire body visible and with detail background.

LORA采用黑森林原版flux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~