Model card auto-generated by SimpleTuner

README.md

@@ -94,8 +94,8 @@ You may reuse the base model text encoder for inference.
 ## Training settings
 
 - Training epochs: 11
-- Training steps: 4500
-- Learning rate: 0.0003
+- Training steps: 4750
+- Learning rate: 0.0001
   - Learning rate schedule: polynomial
   - Warmup steps: 200
 - Max grad norm: 2.0
@@ -104,7 +104,7 @@ You may reuse the base model text encoder for inference.
   - Gradient accumulation steps: 1
   - Number of GPUs: 1
 - Gradient checkpointing: True
-- Prediction type: flow-matching (extra parameters=['flux_schedule_auto_shift', 'shift=0.0', 'flux_guidance_mode=constant', 'flux_guidance_value=1.0', 'flux_beta_schedule_alpha=2.0', 'flux_beta_schedule_beta=5.0', 'flow_matching_loss=compatible'])
+- Prediction type: flow-matching (extra parameters=['flux_schedule_auto_shift', 'shift=0.0', 'flux_guidance_mode=constant', 'flux_guidance_value=1.0', 'flux_beta_schedule_alpha=5.0', 'flux_beta_schedule_beta=2.0', 'flow_matching_loss=compatible'])
 - Optimizer: adamw_bf16
 - Trainable parameter precision: Pure BF16
 - Caption dropout probability: 10.0%
@@ -140,7 +140,7 @@ You may reuse the base model text encoder for inference.
 ### cassatt-512
 - Repeats: 10
 - Total number of images: 16
-- Total number of aspect buckets: 6
+- Total number of aspect buckets: 1
 - Resolution: 0.262144 megapixels
 - Cropped: False
 - Crop style: None