Model card auto-generated by SimpleTuner

README.md

@@ -60,21 +60,21 @@ You may reuse the base model text encoder for inference.
 ## Training settings
 
 - Training epochs: 0
-- Training steps: 100
+- Training steps: 50
 - Learning rate: 0.0001
   - Learning rate schedule: constant
   - Warmup steps: 100
 - Max grad value: 0.01
-- Effective batch size: 3
+- Effective batch size: 1
   - Micro-batch size: 1
   - Gradient accumulation steps: 1
-  - Number of GPUs: 3
+  - Number of GPUs: 1
 - Gradient checkpointing: True
 - Prediction type: flow_matching (extra parameters=['shift=3'])
 - Optimizer: adamw_bf16
 - Trainable parameter precision: Pure BF16
 - Base model precision: `no_change`
-- Caption dropout probability: 10.0%
+- Caption dropout probability: 0.1%
 
 
 - LoRA Rank: 8
@@ -87,8 +87,8 @@ You may reuse the base model text encoder for inference.
 
 ### domokun-cropped-512-NonReg
 - Repeats: 10
-- Total number of images: ~36
-- Total number of aspect buckets: 7
+- Total number of images: 27
+- Total number of aspect buckets: 2
 - Resolution: 0.262144 megapixels
 - Cropped: False
 - Crop style: None
@@ -96,8 +96,8 @@ You may reuse the base model text encoder for inference.
 - Used for regularisation data: No
 ### domokun-cropped-512
 - Repeats: 10
-- Total number of images: ~36
-- Total number of aspect buckets: 2
+- Total number of images: 27
+- Total number of aspect buckets: 1
 - Resolution: 0.262144 megapixels
 - Cropped: False
 - Crop style: None