Trained for 15 epochs and 10000 steps.

Trained with datasets ['text-embed-cache', 'eugene-boudin-sdxl-512', 'eugene-boudin-sdxl-1024', 'eugene-boudin-sdxl-512-crop', 'eugene-boudin-sdxl-1024-crop']
Learning rate 0.0001, 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 sha256:2cae53d5872ce0d704ff7412c5227dc423dc6683c9db50312760169b6d8f23b7
-size 46465680
+oid sha256:495604408cf2e6c1e9e0f3a91478e5310db36fec0f34ad68a693ad7ecc979447
+size 46465608