Trained for 14 epochs and 10000 steps.

Trained with datasets ['text-embed-cache', 'paul-gaugin-sdxl-512', 'paul-gaugin-sdxl-1024', 'paul-gaugin-sdxl-512-crop', 'paul-gaugin-sdxl-1024-crop']
Learning rate 5e-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 sha256:644b04d3abc2c0d4fd448af45d171ec5bfe8ecdf0ab29308fb51c06ad99c62d3
-size 46465680
+oid sha256:b48ae0e6a0a9486ca6aff5ae8e4cd80b4b4c2da106261f82b24d2010c7099367
+size 46465608