Trained for 1 epochs and 500 steps.

Trained with datasets ['encoder-cache', 'juggalos-aspect-bucket', 'juggalos-crop', 'juggalos-aspect-bucket-1mp', 'juggalos-crop-1mp']
Learning rate 5e-06, batch size 6, 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: black-forest-labs/FLUX.1-dev
VAE: None

pytorch_lora_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17aa539f3e4c5b41f2b99498fffa28fafea23bc4f07b73aefcd743149a1d1056
+size 109535132