Trained for 16 epochs and 100 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 sha256:5981e95baf76bbbef5a3cc65655f4afc8f06ad65427561ba9bf4d27b526f5e0e
+oid sha256:0a4bc8c89690df405345a887aaa785451600a3f31201d6ab00f3e011cfc40b22
 size 34833720