---
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
widget:
- text: >-
    (embedding:zPDXL3) (embedding:zPDXLpg) feet out of frame, (close-up,
    portrait:1.3), dappled sunlight, woman, long hair, park, walking, action,
    smiling, wearing a long teal decorative dress, boots, morning sunlight,
    stone ruins, archway, cloudy sky, vines, ivy, flowers
  parameters:
    negative_prompt: >-
      (embedding:zPDXLpg-neg) child, from behind, large breasts, (muscular,)
      wide hips, curvy
  output:
    url: images/2024-08-13-145019_624135700828165.png
- text: >-
    (embedding:zPDXL3) (embedding:zPDXLpg) from below, 1girl, 1boy, blonde hair,
    sitting, heads together, on a tropical beach, smiling, wearing shirt and
    shorts, morning sunlight, tiki hut, palm trees, cloudy sky
  parameters:
    negative_prompt: >-
      (embedding:zPDXLpg-neg) teeth, child, from behind, large breasts,
      (muscular,) wide hips, curvy
  output:
    url: images/2024-08-13-150210_279557614289201.png
base_model: LyliaEngine/Pony_Diffusion_V6_XL
instance_prompt: zPDXL3
license: cdla-permissive-2.0
---
# zPDXL3

<Gallery />

## Model description 

No need to use score this, and score that. Just use the embeddings instead.
New V3 versions only need the one positive embedding!.

A set of quality enhancing embeddings for Pony SDXL, and other Pony-Adjacent models. You can mix and match any of the embeddings that you feel you need. They don&#39;t duplicate each other, so feel free to use as many together as needed.

High Quality V3 (zPDXL3): gives higher quality results and removes annoying censoring.

XXX Rating: tells the Pony model of your choice to allow NSFW content.

PG Rating: tells the Pony model of your choice to try and remove NSFW content for safe images.

Photo Real: tells the Pony model of your choice to use realistic or near realistic renders instead of cartoon or anime.

High Quality V2 (old): designed to give higher quality results and remove censoring.
Doesn&#39;t work with non-Pony models. Check your model.

Recommend using both positive and negative embeddings together at strength 1.0 to 2.0. If you can&#39;t use both, the Positive version should be take priority.

## Source

https://civitai.com/models/332646?modelVersionId=720175

## Credit

https://civitai.com/user/Zovya

## Trigger words

You should use `zPDXL3` to trigger the image generation.


## Download model

Weights for this model are available in Safetensors format.

[Download](/LyliaEngine/zPDXL3/tree/main) them in the Files & versions tab.