Trained for 49 epochs and 11750 steps.

Trained with datasets ['an example backend for text embeds.', 'fsk1']
Learning rate 0.0005, 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: sayakpaul/FLUX.1-merged
VAE: None

pytorch_lora_weights.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eccc32fb1333bc1cac401799c6a9715b25d039008032ef84282878eea8469195
+oid sha256:93d3e49801f4377c441b2544ef2b30dba128be3a678ea75098c42b3cfc65c4aa
 size 104667792