---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- output:
    url: images/99146154.jpeg
  text: '-'

base_model: xinsir/controlnet-union-sdxl-1.0
instance_prompt: SkirtGal, plaid skirt
license: cc-by-nc-sa-2.0
---
# SkirtGals_1

<Gallery />

## Model description 

Gals in skirts, mainly plaid but also some plain pencil skirts too. Trained on SDXL but seems to work for Pony &amp; Illustrious just fine too.

DISCLAIMER: All training data and datasets are synthetic. I have almost no idea what I&#39;m doing with making LORAs, so I can only vouch for what I put in and not what they return. No likeness to real persons were used in training or are intended.
SkirtGal V1: Entirely synthetically trained, no training data was &#39;fully&#39; NSFW&#x2F;Explicit but I have ensured in V1 there&#39;s nothing more than butt cheeks and cleavage, however the models may return NSFW results. LORA is focussed on plaid and pencil skirts in combination with white shirts, tights, ties and blazers. New training method used, model likely overtrained, use low weight

Steps: 18-40
CFG: 3.5-12.0
Sampler: Euler
Scheduler: Normal

## Trigger words

You should use `SkirtGal` to trigger the image generation.

You should use `plaid skirt` to trigger the image generation.


## Download model


[Download](/ApathyGhost/H4nnah/tree/main) them in the Files & versions tab.