Model card auto-generated by SimpleTuner

README.md

@@ -110,8 +110,8 @@ You may reuse the base model text encoder for inference.
 ## Training settings
 
 - Training epochs: 0
-- Training steps: 5500
-- Learning rate: 3e-06
+- Training steps: 5600
+- Learning rate: 6e-06
 - Effective batch size: 16
   - Micro-batch size: 1
   - Gradient accumulation steps: 16
@@ -120,7 +120,7 @@ You may reuse the base model text encoder for inference.
 - Rescaled betas zero SNR: False
 - Optimizer: adamw_bf16
 - Precision: Pure BF16
-- Quantised: Yes: fp8-quanto
+- Quantised: Yes: int8-quanto
 - Xformers: Not used
 - LyCORIS Config:
 ```json
@@ -232,7 +232,7 @@ You may reuse the base model text encoder for inference.
 ### default_dataset_arb
 - Repeats: 9999
 - Total number of images: 41
-- Total number of aspect buckets: 1
+- Total number of aspect buckets: 11
 - Resolution: 1.33 megapixels
 - Cropped: False
 - Crop style: None
@@ -248,7 +248,7 @@ You may reuse the base model text encoder for inference.
 ### default_dataset_arb3
 - Repeats: 9999
 - Total number of images: 3220
-- Total number of aspect buckets: 6
+- Total number of aspect buckets: 43
 - Resolution: 1.33 megapixels
 - Cropped: False
 - Crop style: None