Model card auto-generated by SimpleTuner

README.md

@@ -94,15 +94,15 @@ You may reuse the base model text encoder for inference.
 
 ## Training settings
 
-- Training epochs: 1
-- Training steps: 1250
+- Training epochs: 2
+- Training steps: 1500
 - Learning rate: 7e-05
 - Max grad norm: 0.1
 - Effective batch size: 3
   - Micro-batch size: 3
   - Gradient accumulation steps: 1
   - Number of GPUs: 1
-- Prediction type: flow-matching (extra parameters=['shift=3', 'flux_guidance_value=1.0'])
+- Prediction type: flow-matching (extra parameters=['shift=2.0', 'flux_guidance_value=1.0'])
 - Rescaled betas zero SNR: False
 - Optimizer: adamw_bf16
 - Precision: Pure BF16