Trained for 133 epochs and 2400 steps.

Trained with datasets ['text-embed-cache', 'victorian-crop-512', 'victorian-crop-768']
Learning rate 9e-05, batch size 1, and 2 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 sha256:57090b0f5ca077daf833048d4fed92fdb2d45d0c073fd69cdc33ca62420bc9c1
+oid sha256:fb2ec2f6fc214a8bf5e5142c9185f7513cabcf8c6bf3a1b068e8817de48b7fd5
 size 42324348