Luna_Flex_v3_pony

Epochs == 10

Num Repeats == 2

Train Batch Size == 2

Steps == 10000

Resolution == 1024

LoRA Type == lora

Enable Bucket

Shuffle Tags

Keep Tokens == 0

Clip Skip == 1

Flip Augmentation

Unet LR == 0.0005

Text Encoder LR == 0.00005

LR Scheduler == cosine

LR Scheduler Cycles == 3

Min SNR Gamma == 0

Network Dim == 32

Network Alpha == 32

Noise Offset == 0.03

Optimizer

Prodigy

Optimizer Args == weight_decay=0.5, decouple=True, betas=0.9,0.99, use_bias_correction=False

This my second update to Luna and I will continue to work on updates. Please let me know how I can improve this model.

===================== Pony =========================

Epochs = 12

Num Repeats = 3

Train Batch Size = 5

Steps = 2000

Resolution = 1024

Keep Tokens = 0

Clip Skip = 1

Unet LR = 0.00050

Text Encoder LR = 0.00005

LR Scheduler = cosine

LR Scheduler Cycles = 3

Min SNR Gamma = 0

Network Dim = 32

Network Alpha = 32

Noise Offset = 0.03

Optimizer = Prodigy

Optimizer Args = weight_decay=0.5, decouple=True, betas=0.9,0.99, use_bias_correction=False

並び替え