Trained for 11 epochs and 4200 steps.

Trained with datasets ['text-embed-cache', 'aeb-512', 'aeb-768', 'aeb-1024', 'aeb-1536', 'aeb-crops-512', 'aeb-1024-crop']
Learning rate 0.0001, batch size 3, 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:b91b891d36451689a7ee69985c7e657f2514203e45baf65d939b5e3e71bd11b2
-size 109535068
+oid sha256:c3560546db21e1cdc56653b4d73f1fd614baf6dfd069e0ec5c453aadbcc8f6a8
+size 109535132