models/Kestral PNY by Zovya - V0

Kestral PNY by Zovya - V0

|
10/18/2025
|
5:36:27 PM
| Discussion|
0
Close-up portrait of a happy young girl with a ponytail and yellow headband, wearing a backpack and colorful necklace, standing in an ancient Egypt desert landscape.

Recommended Prompts

score_9,score_8_up,score_7_up

zPDXL, (score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up, high res, 4k)

Recommended Negative Prompts

score_3_up,score_4_up,score_5_up

3d, realistic, (score_3_up, score_4_up, score_5_up, monochrome, vector art, blurry)

Recommended Parameters

samplers

DPM++ 2S a Karras, DPM++ 3M SDE Exponential, DPM++ 2S a, DPM++ 2M

steps

20 - 40

cfg

7 - 9

resolution

768x1152

vae

sdxl_vae_0.9.safetensors

Recommended Hires (High-Resolution) Parameters

upscaler

4x_foolhardy_Remacri

upscale

1.5

denoising strength

0.5

Tips

Experiment with different samplers like DPM++ 2S a Karras for consistency and DPM++ 3M SDE Exponential for more creative results.

Use the score system in prompts to improve quality: positive prompts include score_9, score_8_up, score_7_up and negative prompts include score_3_up, score_4_up, score_5_up.

For easier use, consider the Pony PDXL embeddings available at https://civitai.com/models/332646/pony-pdxl-negative-embeddings.

The goal is to create a Pony model that has bright, crisp, clean characters with beautiful painted backgrounds. Backgrounds have a slight blur to help the characters stand out.

I try to keep my posts Safe for Work (SFW) but this is a pony model and is capable of pony model things.

What it does:

If you're familiar with Pony models, they are very specific in their prompting and subject focus. I made this model to work the same way, but have more stability and a more refined rendering. It uses the same prompting and LoRAs that other PonyXL models use.

What it doesn't do:

It's not a general model. Like other PonyXL models, it's more designed to work with booru tags and mostly does images with people in them. While I have tried to train more landscape images as you can see in the previews.

What's coming:

Continued training for landscapes and backgrounds.

How to use:

You can experiment with different samplers. I prefer DPM++ 2S a Karras for consistency and DPM++ 3M SDE Exponential to get wild. Prompting for quality should use the score system like other PonyXL models. (score_9, score_8_up, score_7_up) in the positive prompt and (score_3_up, score_4_up, score_5_up) in the negative prompt. Otherwise your images will be very plain.

Alternately, you can use the Pony PDXL embeddings that I created for much easier use.

Contributor

Previous
Incursio's Meme Diffusion (SDXL, Pony) - v2.7PDXL
Next
Chroma1-HD-GGUF-&-FP8 - Q8_0

Model Details

Model type

Checkpoint

Base model

Pony

Model version

V0

Model hash

ec6546c95c

Creator

Discussion

Please log in to leave a comment.

Images by Kestral PNY by Zovya - V0

base model Images

ponyxl Images

ponyxl model Images