Trained for 5 epochs and 9500 steps.

Trained with datasets ['text-embeds', 'mikrei-data-512px']
Learning rate 0.0003, batch size 1, 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: terminusresearch/sana-1.6b-1024px
VAE: None

pytorch_lora_weights.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:663a36bb6e81fba88c16a3519aee7e3ffce0d3b8b66a9e2349d445fef4d4651c
+oid sha256:145444ac12ed8be4dc04b1dbc866c8a6d67277eab15a9b211e3de23e37388967
 size 25164904