Trained for 4 epochs and 2400 steps.

Trained with datasets ['text-embed-cache', 'emi-256', 'emi-crop-256', 'emi-512', 'emi-crop-512', 'emi-768', 'emi-crop-768', 'emi-1024', 'emi-crop-1024', 'emi-1440', 'emi-crop-1440']
Learning rate 0.0001, 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.2-dev
VAE: black-forest-labs/FLUX.2-dev

pytorch_lora_weights.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04f736a983858b38bffb5c5dc63e36dabbe09845fd1a8f97dfbcc254c4d9c379
+oid sha256:307a0fccdd1d605310710639614ee0752c01236ccba27941eb51c68f6599271a
 size 213934048