Chiwa Style

🔍 Version info:

Initial release. 64 images and 3072 steps.

📋 Training Parameters:

• Base Model: Pony Diffusion V6 XL

• Training Resolution: 1024

• Training Batch Size: 1

• Type: LoCon

• DIM / Alpha: 16 / 8

• Conv Dim / Alpha: 24 / 6

• Train On: Unet + TE

• Optimizer: Prodigy (weight_decay=0.6,betas=(0.9, 0.99)

• Scheduler: Cosine w/ restarts

• Bucket Resolution: 512 - 2048

• Bucket Steps: 64

• Image Count: 64

• Epochs: 12

• Repeats: 4