Model card auto-generated by SimpleTuner

README.md

@@ -90,7 +90,7 @@ You may reuse the base model text encoder for inference.
 ## Training settings
 
 - Training epochs: 0
-- Training steps: 26000
+- Training steps: 28000
 - Learning rate: 5e-05
 - Max grad norm: 0.01
 - Effective batch size: 5
@@ -1224,8 +1224,8 @@ You may reuse the base model text encoder for inference.
 - Used for regularisation data: No
 ### default_dataset_arb3
 - Repeats: 9999
-- Total number of images: ~4405
-- Total number of aspect buckets: 35
+- Total number of images: ~3305
+- Total number of aspect buckets: 16
 - Resolution: 1.0 megapixels
 - Cropped: False
 - Crop style: None
@@ -1242,7 +1242,7 @@ You may reuse the base model text encoder for inference.
 - Used for regularisation data: No
 ### default_dataset_512
 - Repeats: 9999
-- Total number of images: ~60
+- Total number of images: ~45
 - Total number of aspect buckets: 1
 - Resolution: 0.262144 megapixels
 - Cropped: True
@@ -1269,7 +1269,7 @@ You may reuse the base model text encoder for inference.
 - Used for regularisation data: No
 ### default_dataset_896
 - Repeats: 9999
-- Total number of images: ~80
+- Total number of images: ~45
 - Total number of aspect buckets: 1
 - Resolution: 0.802816 megapixels
 - Cropped: True
@@ -1296,7 +1296,7 @@ You may reuse the base model text encoder for inference.
 - Used for regularisation data: No
 ### default_dataset_art
 - Repeats: 9999
-- Total number of images: ~3420
+- Total number of images: ~2485
 - Total number of aspect buckets: 1
 - Resolution: 1.048576 megapixels
 - Cropped: True
@@ -1305,7 +1305,7 @@ You may reuse the base model text encoder for inference.
 - Used for regularisation data: No
 ### default_dataset_art_512
 - Repeats: 9999
-- Total number of images: ~3950
+- Total number of images: ~3195
 - Total number of aspect buckets: 1
 - Resolution: 0.262144 megapixels
 - Cropped: True
@@ -1314,7 +1314,7 @@ You may reuse the base model text encoder for inference.
 - Used for regularisation data: No
 ### default_dataset_art_640
 - Repeats: 9999
-- Total number of images: ~4220
+- Total number of images: ~3115
 - Total number of aspect buckets: 1
 - Resolution: 0.4096 megapixels
 - Cropped: True
@@ -1323,7 +1323,7 @@ You may reuse the base model text encoder for inference.
 - Used for regularisation data: No
 ### default_dataset_art_768
 - Repeats: 9999
-- Total number of images: ~4285
+- Total number of images: ~2990
 - Total number of aspect buckets: 1
 - Resolution: 0.589824 megapixels
 - Cropped: True
@@ -1332,7 +1332,7 @@ You may reuse the base model text encoder for inference.
 - Used for regularisation data: No
 ### default_dataset_art_896
 - Repeats: 9999
-- Total number of images: ~3815
+- Total number of images: ~2790
 - Total number of aspect buckets: 1
 - Resolution: 0.802816 megapixels
 - Cropped: True