Model card auto-generated by SimpleTuner

README.md

@@ -59,13 +59,13 @@ You may reuse the base model text encoder for inference.
 ## Training settings
 
 - Training epochs: 0
-- Training steps: 1000
-- Learning rate: 0.0001
-  - Learning rate schedule: polynomial
+- Training steps: 500
+- Learning rate: 0.0005
+  - Learning rate schedule: cosine_with_restarts
   - Warmup steps: 100
 - Max grad norm: 2.0
-- Effective batch size: 1
-  - Micro-batch size: 1
+- Effective batch size: 8
+  - Micro-batch size: 8
   - Gradient accumulation steps: 1
   - Number of GPUs: 1
 - Gradient checkpointing: True
@@ -105,7 +105,7 @@ You may reuse the base model text encoder for inference.
 ### my-dataset-256
 - Repeats: 10
 - Total number of images: 71
-- Total number of aspect buckets: 1
+- Total number of aspect buckets: 3
 - Resolution: 0.065536 megapixels
 - Cropped: False
 - Crop style: None
@@ -123,7 +123,7 @@ You may reuse the base model text encoder for inference.
 ### my-dataset-512
 - Repeats: 10
 - Total number of images: 71
-- Total number of aspect buckets: 1
+- Total number of aspect buckets: 6
 - Resolution: 0.262144 megapixels
 - Cropped: False
 - Crop style: None
@@ -141,7 +141,7 @@ You may reuse the base model text encoder for inference.
 ### my-dataset-768
 - Repeats: 10
 - Total number of images: 71
-- Total number of aspect buckets: 1
+- Total number of aspect buckets: 4
 - Resolution: 0.589824 megapixels
 - Cropped: False
 - Crop style: None
@@ -177,7 +177,7 @@ You may reuse the base model text encoder for inference.
 ### my-dataset-1440
 - Repeats: 10
 - Total number of images: 71
-- Total number of aspect buckets: 3
+- Total number of aspect buckets: 4
 - Resolution: 2.0736 megapixels
 - Cropped: False
 - Crop style: None