Flux-BetterLingerie

Trained on 112 handpicked and cropped photos for 60 epochs.
This lora works perfectly with face loras.

The training set doesn't include piercings, tattoos, necklaces and other jewelry.

I would be very grateful if you could leave me your feedback here
and post images with your results.

I would really appreciate it if you guys would leave me

a small Buzz tip here so I can train more Loras.

_______________________________________________________________________________________________

Recommended Settings:

• Distilled CFG Scale:

  • 2-3.5

• Sampling method and Schedule type:

  • I personally use DEIS/Beta.

    You have to decide for yourself if other combinations deliver better results.

• Steps:

  • 30 + HiRes

• Resolution/Aspect Ratio:

  • The Lora is trained on 1:1 and 2:3 aspect ratio.
    You will have to test if other aspect ratios work.

• Lora Weight:

  • 1

• Trigger Word:

  • No Trigger

• Prompting:

  • For the best results, describe the lingerie as detailed as possible.

_______________________________________________________________________________________________

A tip for those who don't know exactly how to describe good lingerie.

Go to: https://huggingface.co/spaces/fancyfeast/joy-caption-alpha-two-vqa-test-one

upload any image with lingerie and let JoyCaption describe your lingerie.