开始尝试FLUX Lora的训练。我之前sd1.5的经验似乎不是很管用了,我现在是个LORA菜鸡。如果使用过程中有什么问题和建议烦请不吝提出,感激不尽。

I started to try the FLUX Lora training. My previous experience with sd1.5 doesn't seem to work very well, I am a rookie for FLUX lora now. If you have any questions or suggestions during use, please do not hesitate to comment. Many thanks!

目前训练的服装都是一个lora一套特定的服装。我想尽量还原服装的细节，所以没有将多套服装融合到一个lora里面。也许将来会尝试融合。

Currently, my training is one lora for one specific costume. I want to restore the details of the costume as much as possible, so I didn't train multiple costumes into one lora. Maybe I will try to merge them in the future.

触发词/Trigger word:

请参考各个版本的说明

Please refer to the description of each version

训练使用了自然语言打标，所以触发词也一定程度上需要自然语言描述。

I use natural language to tag when training, so the trigger words also need natural language.

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~