Trained for 14 epochs and 9000 steps.

Trained with datasets ['text-embed-cache', 'realistic-16-09-512', 'realistic-16-09-1024', 'realistic-16-09-512-crop', 'realistic-16-09-1024-crop']
Learning rate 8e-05, batch size 1, 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 sha256:2f9a97d4dfd3231d14b4f595bd34153c38ddefa9e55bee08f642e8c7328f302e
+oid sha256:54a1452e4d1dde54c267ed8628a34468beb4836eadf8c2ddee08be20ecc33b16
 size 209263048