models/Not Artists Styles for Pony Diffusion V6 XL - Watercolor Anime

Not Artists Styles for Pony Diffusion V6 XL - Watercolor Anime

|
8/30/2025
|
1:20:39 AM
| Discussion|
0
Portrait of a stunning woman with glossy skin and attractive eyes wearing a white top and blue skirt, set against a high contrast background with volumetric light and watercolor effects.
A dark-skinned female fighter with yellow eyes wearing a sleeveless white top and orange pants, posed with fists up and wearing a hood with cat ears in a watercolor style.

Recommended Prompts

score_9, score_8_up, score_7_up, rating_safe, watercolor \(medium\), traditional media, solo, long hair, looking at viewer, standing, 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

other models

Watercolor Anime Style LoRA_Pony XL v6 (d466f107a54d), ponyDiffusionV6XL_v6 (67ab2fd8ec)

Version Highlights

Repeats: 10

Epoch: 5

Image Count: 50

Network Rank (Dimension): 32

Network Alpha: 16

Batch size: 1

Clip skip: 1

Training steps: 2500

Resolution: 768x1024

Train Resolution: 1024,1024

Model: ponyDiffusionV6XL_v6

LR Scheduler: cosine_with_restarts

Optimizer: AdamW8bit

Learning rate: 0,0005

Text Encoder learning rate: 0,00005

Unet learning rate: 0,0005

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

Recommended LoRA Strength (Weight): 0.7-0.8

Trigger Words: watercolor \(medium\), traditional media,

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
Expressive Reasoning - FLUX
Next
Attractive (no trigger) - sliders.ntcai.xyz - v2.0

Model Details

Model type

LORA

Base model

Pony

Model version

Watercolor Anime

Model hash

bf8571cd0e

Trained words

watercolor \(medium\), traditional media,

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 - Watercolor Anime

anime Images

bara Images

digital art Images

female Images

western art Images