Model card auto-generated by SimpleTuner

README.md

@@ -329,13 +329,13 @@ You may reuse the base model text encoder for inference.
 ## Training settings
 
 - Training epochs: 2
-- Training steps: 284000
-- Learning rate: 1e-05
+- Training steps: 285000
+- Learning rate: 5e-05
   - Learning rate schedule: constant
   - Warmup steps: 500
 - Max grad norm: 1.0
-- Effective batch size: 9
-  - Micro-batch size: 3
+- Effective batch size: 12
+  - Micro-batch size: 4
   - Gradient accumulation steps: 1
   - Number of GPUs: 3
 - Gradient checkpointing: True
@@ -377,7 +377,7 @@ You may reuse the base model text encoder for inference.
 ### text-1mp
 - Repeats: 100
 - Total number of images: ~13221
-- Total number of aspect buckets: 2
+- Total number of aspect buckets: 4
 - Resolution: 1.048576 megapixels
 - Cropped: False
 - Crop style: None
@@ -386,7 +386,7 @@ You may reuse the base model text encoder for inference.
 ### signs
 - Repeats: 150
 - Total number of images: ~420
-- Total number of aspect buckets: 2
+- Total number of aspect buckets: 1
 - Resolution: 1.048576 megapixels
 - Cropped: False
 - Crop style: None
@@ -413,7 +413,7 @@ You may reuse the base model text encoder for inference.
 ### shutterstock
 - Repeats: 0
 - Total number of images: ~21111
-- Total number of aspect buckets: 13
+- Total number of aspect buckets: 35
 - Resolution: 1.048576 megapixels
 - Cropped: False
 - Crop style: None
@@ -422,7 +422,7 @@ You may reuse the base model text encoder for inference.
 ### cinemamix-1mp
 - Repeats: 0
 - Total number of images: ~7425
-- Total number of aspect buckets: 3
+- Total number of aspect buckets: 5
 - Resolution: 1.048576 megapixels
 - Cropped: False
 - Crop style: None
@@ -431,7 +431,7 @@ You may reuse the base model text encoder for inference.
 ### anatomy
 - Repeats: 5
 - Total number of images: ~16440
-- Total number of aspect buckets: 2
+- Total number of aspect buckets: 24
 - Resolution: 1.048576 megapixels
 - Cropped: False
 - Crop style: None
@@ -467,7 +467,7 @@ You may reuse the base model text encoder for inference.
 ### shutterstock-512
 - Repeats: 0
 - Total number of images: ~21096
-- Total number of aspect buckets: 7
+- Total number of aspect buckets: 19
 - Resolution: 0.262144 megapixels
 - Cropped: False
 - Crop style: None
@@ -485,7 +485,7 @@ You may reuse the base model text encoder for inference.
 ### anatomy-512
 - Repeats: 5
 - Total number of images: ~16437
-- Total number of aspect buckets: 3
+- Total number of aspect buckets: 13
 - Resolution: 0.262144 megapixels
 - Cropped: False
 - Crop style: None
@@ -494,7 +494,7 @@ You may reuse the base model text encoder for inference.
 ### signs-1440
 - Repeats: 100
 - Total number of images: ~423
-- Total number of aspect buckets: 25
+- Total number of aspect buckets: 1
 - Resolution: 2.0736 megapixels
 - Cropped: False
 - Crop style: None
@@ -521,7 +521,7 @@ You may reuse the base model text encoder for inference.
 ### shutterstock-1440
 - Repeats: 0
 - Total number of images: ~21111
-- Total number of aspect buckets: 19
+- Total number of aspect buckets: 44
 - Resolution: 2.0736 megapixels
 - Cropped: False
 - Crop style: None
@@ -530,7 +530,7 @@ You may reuse the base model text encoder for inference.
 ### cinemamix-1mp-1440
 - Repeats: 0
 - Total number of images: ~7425
-- Total number of aspect buckets: 3
+- Total number of aspect buckets: 5
 - Resolution: 2.0736 megapixels
 - Cropped: False
 - Crop style: None
@@ -539,7 +539,7 @@ You may reuse the base model text encoder for inference.
 ### anatomy-1440
 - Repeats: 5
 - Total number of images: ~16458
-- Total number of aspect buckets: 2
+- Total number of aspect buckets: 34
 - Resolution: 2.0736 megapixels
 - Cropped: False
 - Crop style: None