Trained for 4 epochs and 4800 steps.

Trained with datasets ['text-embed-cache', 'frankpape-512', 'frankpape-768', 'frankpape-1024', 'frankpape-1536']
Learning rate 0.0003, batch size 4, 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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aff2d4ecbf373452581c8c6611f766544629ae37b63d2fe543ad5dd28cf23c84
+oid sha256:ff0383e9a27d89a1c52509556c5983ad97fdca3b186a2762f37e28d1bbfa77d4
 size 109535132