Home Artists Posts Import Register

Downloads

Content

I consider tiny shorts as one of the greatest human inventions 🍑

🖼️ See some examples 🖼️

This model deserves a new version, but you can already enjoy it a lot ...

⚖️LoRA prompt weight: 0.6~0.8
⚙️~60% effectiveness
🏫Model used for training: CyberRealisticV3

🔍Recomendations:

  • CFG ~9
  • Steps >=35
  • All Samplers

Start your prompts with:

[photo type] of [woman], [body characteristics], [face characteristics], [position], [clothing and hair], [short details], realistic...

Recommended starting neg with:

(selfie, smartphone, phone, close-up:1.3)...

🌟Tutorial for improving results.

LoRA details and tendencies (+resolution):

  • I achieved good results with these neg embeddings: CyberRealistic_Negative-neg and FastNegative. But you can use normal neg prompts.
  • This Lora can cause some face problems, I recommend inpaint them without the LoRA prompt or use Adetailer, check improvement link to learn how you can use that.
  • Sometimes the subject tends to stay in the selfie pose, "selfie, smartphone, phone" on neg resolve that.
  • This LoRA have a tendency of close-up on ass. "close-up" on neg and "full body photo" on pos can improve results.

Inside the folder I left some example images and tags used for training, you can use this on your prompts.

Comments

No comments found for this post.