Trained for 4 epochs and 3000 steps.

Trained with datasets ['text-embed-cache', 'jss-sdxl-512', 'jss-sdxl-1024', 'jss-sdxl-512-crop', 'jss-sdxl-1024-crop']
Learning rate 8e-05, batch size 8, 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 sha256:2aeda778ca5b1c399a03027e87641aeff8df50cc7566c24d0579df61e6fc1cde
+oid sha256:4ba4caed69b0d4f247eee6803d0acbbf42fb313ef3ee2c73cffe2dad37893b87
 size 185964888