models/Not Artists Styles for Pony Diffusion V6 XL - Photo 2

Not Artists Styles for Pony Diffusion V6 XL - Photo 2

|
11/16/2025
|
11:54:28 AM
| Discussion|
0
Young man looking upward under a bright blue sky filled with floating intricate bubbles and sunlight shining through.
A detailed animated medieval warrior in armor standing on a rocky landscape at sunset, created using Stable Diffusion.

Recommended Prompts

score_9, score_8_up, score_7_up, raw, photo, realistic, solo, long hair, looking at viewer, outdoors

Recommended Negative Prompts

score_6_up, score_5_up, score_4_up, 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 (27d98dcc64)

other models

Photo 2 Style SDXL_LoRA_Pony Diffusion V6 XL (19f2fc550f8d), ponyDiffusionV6XL_v6 (67ab2fd8ec)

Tips

Recommended LoRA Strength (Weight): 0.8-1

Preview generated without using ADetailer & Hires. fix

Version Highlights

Repeats: 5

Epoch: 4

Image Count: 300

Network Rank: 32

Network Alpha: 16

Batch size: 2

Clip skip: 1

Training steps: 3000

Resolution: 768x1024

Train Resolution: 1024x1024

Model: ponyDiffusionV6XL_v6

Captioning: WD14 Captioning + Edit (SmilingWolf/wd-v1-4-moat-tagger-v2)

Trigger Words: raw, photo, realistic,

LoRA Weight: [0.8-1]

Without the tokens raw, photo, realistic, the model will generate 2.5D-3D and sometimes 2D styles, these tokens should be at the beginning after the score, if you can't get a realistic style, you're doing something wrong try to change the prompt

The preview should show that the first image is with Trigger Words and the second image is just with LoRA

Score, Trigger Words, Prompt

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
MorphXL - v1.0
Next
Sinister Style SDXL - v1.0

Model Details

Model type

LORA

Base model

Pony

Model version

Photo 2

Model hash

979cbe2ec4

Trained words

raw, photo, realistic,

Creator

Discussion

Please log in to leave a comment.

Model Collection - Not Artists Styles for Pony Diffusion V6 XL

Images by Not Artists Styles for Pony Diffusion V6 XL - Photo 2

anime Images

bara Images

digital art Images

female Images

western art Images