Trained for 5 epochs and 7600 steps.

Trained with datasets ['text-embed-cache', 'marco-256', 'marco-crop-256', 'marco-512', 'marco-crop-512', 'marco-768', 'marco-crop-768', 'marco-1024', 'marco-crop-1024', 'marco-1440', 'marco-crop-1440']
Learning rate 8e-05, batch size 3, 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:be0c6f3311b5cc8da3e2569007c61af0ae689089277756fc6d366ddc9e3e2e89
+oid sha256:efdcf6baa88018bed6880cd1637b7d192fbfe3d17d147ef7c02ecd188e93aa9b
 size 209263048