Trained for 6 epochs and 600 steps.

Trained with datasets ['text-embed-cache', 'test-dataset-512', 'test-dataset-1024', 'test-dataset-512-crop', 'test-dataset-1024-crop']
Learning rate 0.0001, batch size 16, 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: Lykon/dreamshaper-xl-v2-turbo
VAE: madebyollin/sdxl-vae-fp16-fix

pytorch_lora_weights.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:240c49173507ee6aad1f80361633490e1412b99796b0ae7f970e0fd77aba92f9
-size 335205320
+oid sha256:f70d7aa1a5eab6b881e547244e421f2ff31f5ec29b17227d31a28883f67a864d
+size 335205256