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 = 12Num Repeats = 3Train Batch Size = 5Steps = 2000Resolution = 1024Keep Tokens = 0Clip Skip = 1Unet LR = 0.00050Text Encoder LR = 0.00005LR Scheduler = cosineLR Scheduler Cycles = 3Min SNR Gamma = 0Network Dim = 32Network Alpha = 32Noise Offset = 0.03Optimizer = ProdigyOptimizer Args = weight_decay=0.5, decouple=True, betas=0.9,0.99, use_bias_correction=False

Luna_Flex_v3_pony

Fine-tuned this model with generated images

Files with SHA256: 0d1d0d3504a2ae3e0cc20cfebbfef1c619e5f0f6caeef23766847f03dff796e5