Trained for 4 epochs and 2500 steps.

Trained with datasets ['text-embed-cache', 'iwatch-256', 'iwatch-crop-256', 'iwatch-512', 'iwatch-crop-512', 'iwatch-768', 'iwatch-crop-768', 'iwatch-1024', 'iwatch-crop-1024', 'iwatch-1440', 'iwatch-crop-1440']
Learning rate 8e-05, batch size 2, 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:d624aa1b941c47df3d17bf11ea4a71eff21b4e459ee858f7665c66ea8ca58c18
+oid sha256:0c58b69dbc87f8241089a331192f43c996d54a0a4c00f905dfc144e80cc4fdf4
 size 209263808