这篇帖子是 初音未来 各种cosplay服装FLUX.1 D的LORA集合(包含官设和同人)。
This post is a collection of Hatsune Miku cosplay costumes FLUX.1 D LORA (including official and doujin).
你可以在这找到sd1.5的版本/You can find sd1.5 version here: Hatsune Miku cosplay costume collection | 初音未来 cosplay 服饰合集
触发词/Trigger word (示例图片触发词/Sample images trigger words):
请参考各个版本的说明
Please refer to the description of each version
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’
LORA uses the original Black Forest Labs FLUX as the base model for training. When using it, the LORA Strength can be directly set to ‘1.00’
这个模型主要聚焦在服饰，脸部不在预期训练范围内。你可以搭配其他脸部lora或者使用facedetailer来进行脸部重绘。效果图我使用了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）
This model mainly focuses on clothing, and the face is not in the intended training range. You can use face Lora or use facedetailer to repaint the face. I used FaceDetailer to repaint the sample images.
My workflow for sample image is:
FLUX official demo workflow generate 1152*1536 iamges directly -> SD1.5 FaceDetailer (personally I prefer sd1.5 face, you can repaint it according to your preference)
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~
Sincerely invite you to try this Lora. I am eager for your feedback and comment. It would be great if you can share the beautiful images generated by this lora. Thanks~
Description
触发词/Trigger word:
a woman in hatsune miku cosplay attire, she is wearing shirt with detached sleeves and necktie and pleated skirt and thigh boots, she has shoulder tattoo and a very long aqua twintails with hair ornament and headset
示例图片触发词:
an beautiful slim girl in hatsune miku cosplay attire, full length shot, full body, she is wearing shirt with detached sleeves and necktie and pleated skirt and thigh boots, she has shoulder tattoo and a very long aqua twintails with hair ornament and headset, Standing on the roof of the building at night, Behind is the neon cityscape
FAQ
Comments (5)
are you planning to stop making lora for SD 1.5?
I am not sure. I am trying Flux now. Sry, I don't have much energy to train both of them. Renting cloud GPU services for training is also a considerable expense.
Or do you have any particular costume you want for 1.5, I will try to train it for you.
I like and appreciate your work with LoRA SD 1.5 cosplay from HoYoverse characters. I hope you keep updating your work with new characters as usual. My computer only has 4GB VRAM, so I can only try SD 1.5, and cloud services aren’t as flexible as personal computers, so I'm not interested in subscribing. But, if I may request, maybe you could add characters from HI3rd like Kiana Kaslana or from the SAO anime like Yuuki Asuna.
@ai_nkftnh Many thanks for your like. I Understand you. Generating images on my PC with Flux is also very demanding. I can quickly produce many example images for SD1.5, while Flux takes a very long time to generate just one. However, these past few days, I've come to feel that the learning effectiveness of Flux is indeed much better than SD1.5.
I also really like the characters from HI3rd, just as my username , you should know that this is the name of Bronya's song. In fact, I have tried training characters from HI3rd for sd1.5, like Elysia. However, I have always struggled to find good training materials, failing to achieve the desired results.
Perhaps in the future, I will further explore. But for now, I want to focus more on experimenting with Flux LORA training first.
Good luck with your LoRA flux training, I also like your work on LoRA cosplay hatsune miku especially the school uniform, I often modify it with the short sleeve version.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.