PixAI Membership
PixAI
PixAI
Generate
Sign in
Home
Generation
Models
Studio
NEW
Contest
Create with Mio.2
AI Tools
NEW
Guide

User LoRA

SD

BetterDeepSkin (BDS)

#Skindentation
AI Tools
  • AI Anime Generator
  • Anime Figure Generator
  • Character Sheet Generator
  • Magazine Cover Generator
  • Plushie Generator
  • Giant Statue Generator

Discover

  • Trending Tags
  • Ranking
  • Model Market
  • Contest
  • News

About

  • Guide
  • PixAI Blog
  • Tsubaki.2
  • Meet Mio, Our Mascot
  • Content Rules

Pricing & Help

  • Membership
  • Buy Credits
  • Contact

Mobile App

  • Get the PixAI app
  • App Store
  • Google Play
© 2026 PixAI
  • Terms of Service
  • Privacy Policy
  • Copyright Policy
  • Attributions
  • Specified Commercial Transactions Law
Mio with expression sulk

Oops, this cover can't be shown

It didn't pass our content check — no worries, your model is still fully searchable and usable! Just swap in a cover that works for everyone.

Uploaded at
Jun 19, 2023, 9:50 PM
Uses
4.1k
Reviews
No reviews
Trigger Words

BDS

Permissions
  • Allow image generation & sharing
  • Allow users to download this model
  • Allow commercial use of generated images

Description

https://civitai.com/models/89831/betterdeepskin-bds A Lora trained on various images with the deep_skin tag. Think it can sometimes make better breasts, though all this "better" stuff is subjective. Its more breast focused but can do other body parts. If using other Loras I would recommend messing with the weights as having both at 1 can cause too much skindentationing. (can also add texture to clothing) weights 0.7 - 1.0 recommended tags: deep_skin, skindentation optional tags: pov, pov_hands, breast_grab, breast_lift, ass_grab (pretty much anything involving skin indents)

optional negatives: thick, thick_thighs, fat, shiny, shiny_skin, wet (can create really thick people sometimes or shiny skin)

got worse results when using bad-hands-5.

discovered issues: Not sure if it is this model or my main checkpoint, but sometimes the skin will become a solid color - think it is my checkpoint.

Had some paizuri images in the dataset, so put paizuri in the negative if it gens it

Comments