Trained for 12 epochs and 500 steps.

Trained with datasets ['text-embed-cache', 'hidream-test-dataset-256', 'hidream-test-dataset-crop-256', 'hidream-test-dataset-512', 'hidream-test-dataset-crop-512', 'hidream-test-dataset-768', 'hidream-test-dataset-crop-768', 'hidream-test-dataset-1024', 'hidream-test-dataset-crop-1024']
Learning rate 0.0001, 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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dbb29068999b0f0e8a6bf9d88aac62ab1db3cecdf86d8610a543b6feefcb71e
+size 358745556