Trained for 44 epochs and 90 steps.

Trained with datasets ['an example backend for text embeds.', 'antelope-data-1024']
Learning rate 0.0001, batch size 1, and 1 gradient accumulation steps.
Trained with epsilon prediction type and rescaled_betas_zero_snr=False
Using 'trailing' timestep spacing.
Base model: terminusresearch/pixart-900m-1024-ft-v0.6
VAE: madebyollin/sdxl-vae-fp16-fix

pytorch_lora_weights.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caeb86d9b7da878e7e76f97241b8cafcc6a2cc70211bc724c351b97e838d3283
+oid sha256:84abfbd3394410d318ea0c84f4c798f0aa5bc94d0986cb270b4bae8cb8e2202f
 size 34834136