Found on Danbooru, yur oc like this (meme) / pec pov (meme) and thought why not make LoRA
v1.0 - Trained on 20 Images from Danbooru
v1.1 - Trained on 30 Images from Danbooru, Added noise token to captions, noise you can add to Negative prompt
v1.1 U (Updated) - In this version, Trigger Word and Captions have been changed.
It works with humans, furries, ponies. You can generate characters without tank top
This LoRA can generate males as well as females.
Preview generated without using ADetailer & Hires. fix
Recommended LoRA Strength (Weight): 0.8-1
Description
Repeats: 10
Epoch: 20
Image Count: 30
Network Rank: 32
Network Alpha: 16
Batch size: 2
Clip skip: 1
Training steps: 3000
Resolution: 1024x1024
Train Resolution: 1024x1024
Model: ponyDiffusionV6XL_v6
Captioning: WD14 Captioning + Edit (SmilingWolf/wd-v1-4-moat-tagger-v2)
Trigger Words: mns-pose,
LoRA Weight: [0.7-1]


















