Model card auto-generated by SimpleTuner

README.md

@@ -95,11 +95,11 @@ You may reuse the base model text encoder for inference.
 ## Training settings
 
 - Training epochs: 0
-- Training steps: 700
-- Learning rate: 0.0002
-- Effective batch size: 12
+- Training steps: 800
+- Learning rate: 0.0003
+- Effective batch size: 6
   - Micro-batch size: 2
-  - Gradient accumulation steps: 2
+  - Gradient accumulation steps: 1
   - Number of GPUs: 3
 - Prediction type: flow-matching
 - Rescaled betas zero SNR: False
@@ -137,7 +137,7 @@ You may reuse the base model text encoder for inference.
 ### sfwbooru
 - Repeats: 0
 - Total number of images: ~639264
-- Total number of aspect buckets: 77
+- Total number of aspect buckets: 81
 - Resolution: 1.048576 megapixels
 - Cropped: False
 - Crop style: None