Trained for 2 epochs and 6400 steps.

Trained with datasets ['text-embed-cache', 'hiroshige-sdxl-512', 'hiroshige-sdxl-1024', 'hiroshige-sdxl-512-crop', 'hiroshige-sdxl-1024-crop']
Learning rate 6e-05, batch size 4, and 1 gradient accumulation steps.
Used DDPM noise scheduler for training with epsilon prediction type and rescaled_betas_zero_snr=False
Using 'trailing' timestep spacing.
Base model: stabilityai/stable-diffusion-xl-base-1.0
VAE: madebyollin/sdxl-vae-fp16-fix

pytorch_lora_weights.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61e8e15afcb2a8aceb553a5aaa9c7fcaa3fd07b9135eb462a684511c881e02ca
+oid sha256:72d967b130ab9a1bbdd2d462f36a7d7bc171102d4bf33670ce4af5565055e8ca
 size 46465680