Model card auto-generated by SimpleTuner

README.md

@@ -93,10 +93,10 @@ You may reuse the base model text encoder for inference.
 
 ## Training settings
 
-- Training epochs: 10
-- Training steps: 4000
-- Learning rate: 0.0006
-  - Learning rate schedule: polynomial
+- Training epochs: 11
+- Training steps: 4200
+- Learning rate: 0.0001
+  - Learning rate schedule: constant
   - Warmup steps: 200
 - Max grad norm: 2.0
 - Effective batch size: 3
@@ -140,7 +140,7 @@ You may reuse the base model text encoder for inference.
 ### aeb-512
 - Repeats: 12
 - Total number of images: 21
-- Total number of aspect buckets: 1
+- Total number of aspect buckets: 4
 - Resolution: 0.262144 megapixels
 - Cropped: False
 - Crop style: None
@@ -158,7 +158,7 @@ You may reuse the base model text encoder for inference.
 ### aeb-1024
 - Repeats: 5
 - Total number of images: 21
-- Total number of aspect buckets: 4
+- Total number of aspect buckets: 1
 - Resolution: 1.048576 megapixels
 - Cropped: False
 - Crop style: None
@@ -167,7 +167,7 @@ You may reuse the base model text encoder for inference.
 ### aeb-1536
 - Repeats: 2
 - Total number of images: 21
-- Total number of aspect buckets: 1
+- Total number of aspect buckets: 4
 - Resolution: 2.359296 megapixels
 - Cropped: False
 - Crop style: None