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

User LoRA

XL
Character

Leydia Witch [Dark Souls 2]

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
Leydia Witch [Dark Souls 2] - AI Model cover image
Uploaded at
Apr 4, 2026, 7:50 PM
Uses
3
Reviews
No reviews
Trigger Words

Le8d1a, colored skin, grey skin, covered eyes, black lips, sharp fingernails, crown, hooded robe, hood up, black hood, black robe, torn clothes, grey long scarf, holding weapon

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

Description

A model of Leydia Witch, trained over 22 images for 1024 using NoobAI Epsilon-pred 1.1 as a training modelTrigger word: Le8d1aLooks tags: colored skin, grey skin, covered eyes, black lips, sharp fingernails, crown, hooded robe, hood up, black hood, black robe, torn clothes, grey long scarfOptional tag: holding weaponWeight:1- 0.8 you would get more of the ingame style0.7 - 0.6 this should be your starting point0.5 and below, they affect are very minimalcheck image comparison in the end for more detailAdditional information:Webui I useAAA Anime VAE SDXL v2 as VAESampling method: Euler aSchedule type I set it to SGM UniformSampling steps I go 20-304xNomos8kDAT as an UpscalerHires steps I go 8-15 (I don't always use hires fix)Denoising strength I go 0.4Upscale by 1.2 to 2.0 depending on the starting image dimensionsImagine dimensions vary depending on what I'm trying to doI use 6 CFG Scaleuddetailer for faces, I use mediapipe_face_mesh set Dilation to 50 and Y offset to 30 to get the full faceIf you wanna support me ko-fi

Comments