🔍 Version info:
Reworked the dataset and training parameters. 110 images and 15400 steps.
📋 Training Parameters:
Base Model: Pony Diffusion V6 XL
Training Resolution: 1024
Training Batch Size: 1
Type: LoCon
DIM / Alpha: 32 / 16
Conv Dim / Alpha: 24 / 6
Train On: Unet + TE
Optimizer: AdamW8bit
Scheduler: Cosine w/ restarts
Min SNR Gamma: 8
Bucket Resolution: 512 - 2048
Bucket Steps: 64
Noise Offset: Normal (0.035)
Image Count: 110
Epochs: 14
Repeats: 10
🔍 Version info:
Reworked the dataset and training parameters. 110 images and 15400 steps.
📋 Training Parameters:
Base Model: Pony Diffusion V6 XL
Training Resolution: 1024
Training Batch Size: 1
Type: LoCon
DIM / Alpha: 32 / 16
Conv Dim / Alpha: 24 / 6
Train On: Unet + TE
Optimizer: AdamW8bit
Scheduler: Cosine w/ restarts
Min SNR Gamma: 8
Bucket Resolution: 512 - 2048
Bucket Steps: 64
Noise Offset: Normal (0.035)
Image Count: 110
Epochs: 14
Repeats: 10