LoRA is trained on 44 images from Classic Dad & Classic Dad Plus
Preview generated without using ADetailer & Hires. fix
Recommended LoRA Strength (Weight): 0.8-0.9
v1.1 - I improved the upscale and edited the images, I also changed the captions a little and added tags, flat color, toon\(style\) to make the style more stable, flat color is optional. Do not use toon \(style\), for NoobAI-XL EPS 1.0 (it is not necessary and the result may be worse)
v1.0 - the first release
Description
Repeats: 10
Epoch: 6
Image Count: 44
Network Rank (Dimension): 16
Network Alpha: 8
Batch size: 1
Clip skip: 1
Model: ponyDiffusionV6XL_v6
Training steps: 2640
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
Captioning: WD14 Captioning (SmilingWolf/wd-v1-4-moat-tagger-v2) + Edit
Trigger Words: classicdadvk,
Recommended LoRA Strength (Weight): 0.8-0.9