Model card auto-generated by SimpleTuner

README.md

@@ -108,8 +108,8 @@ You may reuse the base model text encoder for inference.
 ## Training settings
 
 - Training epochs: 0
-- Training steps: 1000
-- Learning rate: 0.0006
+- Training steps: 100
+- Learning rate: 0.0004
 - Effective batch size: 16
   - Micro-batch size: 1
   - Gradient accumulation steps: 16
@@ -131,7 +131,8 @@ You may reuse the base model text encoder for inference.
     "factor": 10,
     "apply_preset": {
         "target_module": [
-            "FluxTransformer2DModel"
+            "FluxSingleTransformerBlock",
+            "FluxTransformerBlock"
         ],
         "module_algo_map": {
             "FeedForward": {
@@ -163,7 +164,7 @@ 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: 4
+- Total number of aspect buckets: 26
 - Resolution: 1.33 megapixels
 - Cropped: False
 - Crop style: None