Trained for 56 epochs and 5000 steps.

Trained with datasets ['text-embed-cache', 'glssrxdsndsn_flat-512', 'glssrxdsndsn_flat-768', 'glssrxdsndsn_flat-1024']
Learning rate 0.0002, batch size 2, 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:e17572e7f3c9763aeea3546cc420e51bd5ec7ebb4f8e7d3206009580a1b090e6
-size 160100540
+oid sha256:54b067fffc147aa2250b7ef46b71ba6915f84e67e8e912870f832a0b2442bf5c
+size 160100476