models/Styles for Pony Diffusion V6 XL Not Artists styles - Photo

Styles for Pony Diffusion V6 XL Not Artists styles - Photo

|
7/1/2024
|
11:51:04 PM
| Comments

Recommended Prompts

Summer Night,Cold Oil Gothic,Digital Art

score_9,score_8_up,score_7_up,solo,looking at viewer

Recommended Negative Prompts

text,watermark,low-quality,signature,moiré pattern,downsampling,aliasing,distorted,blurry,glossy,blur,jpeg artifacts,compression artifacts,poorly drawn,low-resolution,bad,distortion,twisted,excessive,exaggerated pose,exaggerated limbs,grainy,symmetrical,duplicate,error,pattern,beginner,pixelated,fake,hyper,glitch,overexposed,high-contrast,bad-contrast

Recommended Parameters

samplers

DPM++ 2M SDE Karras

steps

35

cfg

5

resolution

768x1152

vae

sd_xl_0.9.vae.pt (9bc1af5a15)

other models

Photo Style LoRA XL (e84db89df1), ponyDiffusionV6XL_v6 (67ab2fd8ec)

Tips

CLIP SKIP settings can vastly affect the output.

Use 'Summer Night' for dark themes and low light effects.

Tokens like 'Cold Oil Gothic' and 'Concept Art Twilight' enhance the artistic style.

Version Highlights

Repeats: 20

Epoch: 10

Image Count: 22

Network Rank: 32

Network Alpha: 16

Batch size: 2

Clip skip: 1

Training steps: 2200

Resolution: 1024x1024

Model: ponyDiffusionV6XL_v6

WD14 Captioning

SmilingWolf/wd-v1-4-convnextv2-tagger-v2

LoRA Weight: [0.8-0.1]

Creator Sponsors

This asset is designed to work best with the Pony Diffusion XL model, it will work with other SDXL models but may not look as intended.

Styles are trained on synthetic data and do not copy the styles of artists!

Photo 2 - is trained on real data (Dataset from Unsplash)

[M] Merged LoRAs

Recommended LoRA Strength (Weight): 0.8-1

Preview generated without using ADetailer & Hires. fix

Previous
xl_more_artfull xl_real Enhancer - xl_more_artfullv1
Next
Quality Embeddings For Furries - Quality bwu

Model Details

Model type

LORA

Base model

Pony

Model version

Photo

Model hash

bd9a91aa94

Trained words

realistic,

Creator