Trained for 0 epochs and 500 steps.

Trained with datasets ['text-embed-cache', 'ben-brand-256', 'ben-brand-crop-256', 'ben-brand-512', 'ben-brand-crop-512', 'ben-brand-768', 'ben-brand-crop-768', 'ben-brand-1024', 'ben-brand-crop-1024', 'ben-brand-1440', 'ben-brand-crop-1440']
Learning rate 0.0001, batch size 2, and 3 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 sha256:1e0e19c3a9cabd19481c4c1361a3d1cbb8890d093934ddab32a25974364b27a2
+size 209263048