What should I say?
Have fun!

_______________________________________________________________________________________________

The Lora was trained with 100 photos.

_______________________________________________________________________________________________

Recommended Settings:

• Distilled CFG Scale:

  • between 2-3.5 (depending on your own taste)

• Sampling method and Schedule type:

  • I personally use Euler/Simple.

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

• Steps:

  • 20-30

• Resolution/Aspect Ratio:

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

• Lora Weight:

  • 0.1-1
    But again, it all depends on your own taste.

• Trigger:

  • peachy ass
    Also works without trigger.
    But if you have only entered “woman, hair, clothing, etc. etc.” in your prompt,
    then use “peachy ass” to trigger the view from behind.

• Prompt:

  • Use a prompt of your choice.
    I tested it with short tags and with long natural language.
    Both gave me good results.

_______________________________________________________________________________________________

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