Trained for 6 epochs and 3000 steps.

Trained with datasets ['text-embed-cache', 'davinci-sdxl-512', 'davinci-sdxl-1024', 'davinci-sdxl-512-crop', 'davinci-sdxl-1024-crop']
Learning rate 7e-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 sha256:3d8c28a01e3ef24c21c52ebff25b54b6c96e51d4bb1507c1ac8e6b7a9d3cd2ed
+oid sha256:d5bda9a0dd07fcb51ed9609af945b0d74b8b43762849b7254a7e7099f0b6c364
 size 46465680