Trained for 0 epochs and 400 steps.

Trained with datasets ['text-embed-cache', 'liqglass-dataset']
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.2-klein-base-4B
VAE: black-forest-labs/FLUX.2-klein-base-4B

pytorch_lora_weights.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e20c24d507d13c45fd81e73d65016b10e23ba3d5da7e0f9f1b59d38cf7e48a6b
+oid sha256:f4e86d0482ca374c2bc905f579fc73261213f93d6cd83d0517fbd5ba2f027fa8
 size 11809760