Petra Voice Styles [LoRA]版本v1.0 Original (ID: 599820)

Petra Voice is an artist who uses AI to create her works of art

These styles are well suited for creating portraits, you can create both girls and boys

Preview generated without using ADetailer & Hires. fix

Recommended LoRA Strength (Weight): 0.7-1

ㅤ

About Styles

Cult of Tales - With this style, you can create mysterious and creepy portraits. You can create scary monster girls, or girls standing next to monsters

A few tags that can help to create images - pale skin, pointy ears, horns, branches, thorns, monster girl, transformation, simple background, gradient background,

v1.0 - With these styles, you can create very cute and interesting portraits.

Original - Original images with noise

DeNoise - Edited images without noise

Mix - Mixing Original and DeNoise LoRAs 50/50

ㅤ

I disclaim responsibility for how this LoRAs will be used.

描述:

Repeats: 5

Epoch: 5

Image Count: 100

Network Rank (Dimension): 16

Network Alpha: 8

Batch size: 1

Clip skip: 1

Training steps: 2500

Resolution: 1024x1024

Train Resolution: 1024,1024

LR Scheduler: cosine_with_restarts

Optimizer: AdamW8bit

Learning rate: 0,0005

Text Encoder learning rate: 0,00005

Unet learning rate: 0,0005

Model: ponyDiffusionV6XL_v6

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

Trigger Words: petravoicestyle,

Recommended LoRA Strength (Weight): 0.7-1

训练词语: petravoicestyle, chromatic aberration, film grain,