Trained for 1 epochs and 150 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:e86a2c5d0507fcba3adfc27475c3ab9cdc2f3f51ab5c7e3346b3fb723d0f9a90
-size 335205320
+oid sha256:107852502e6ab26c0d3274833e1a90bff0d1b040e60f8a4a71eac46b129f00e9
+size 335205256