Trained for 5 epochs and 3500 steps.

Trained with datasets ['text-embed-cache', 'my-dataset-256', 'my-dataset-crop-256', 'my-dataset-512', 'my-dataset-crop-512', 'my-dataset-768', 'my-dataset-crop-768', 'my-dataset-1024', 'my-dataset-crop-1024', 'my-dataset-1440', 'my-dataset-crop-1440']
Learning rate 4e-05, batch size 1, and 1 gradient accumulation steps.
Trained with None prediction type and rescaled_betas_zero_snr=False
Using 'trailing' timestep spacing.
Base model: black-forest-labs/FLUX.1-dev
VAE: black-forest-labs/FLUX.1-dev

pytorch_lora_weights.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5ee46ab671e91dd67c06f5e673583dfc7267f33bb36ea9acfebf6037c858455
+oid sha256:03791837c534a191ace5c934d487726ee106219d0c82561fd4623cc6b50922a7
 size 109535132