Update README.md

README.md

@@ -74,14 +74,20 @@ As same as kxl eps rev2, I add realbooru and pvc figure images for more flexibil
 
 ## Training
 - Hardware: Quad RTX 3090s
+- Dataset
+  - Num Images: 8,468,798
+  - Resolution: 1024x1024
+  - Min Bucket Resolution: 256
+  - Max Bucket Resolution: 4096
+  - Caption Tag Dropout: 0.2
+  - Caption Group Dropout: 0.2 (for dropping tag/nl caption entirely)
 - Training
-  - Num Train Images: 8,468,798
-  - Total Epoch: 1
-  - Total Steps: 16548
-  - Training Time: 430 hours (wall time)
   - Batch Size: 4
   - Grad Accumulation Step: 32
   - Equivalent Batch Size: 512
+  - Total Epoch: 1
+  - Total Steps: 16548
+  - Training Time: 430 hours (wall time)
   - Mixed Precision: FP16
 - Optimizer
   - Optimizer: Lion8bit
@@ -94,12 +100,6 @@ As same as kxl eps rev2, I add realbooru and pvc figure images for more flexibil
   - Min SNR Gamma: 5
   - Debiased Estimation Loss: Enabled
   - IP Noise Gamma: 0.05
-  - Resolution: 1024x1024
-  - Min Bucket Resolution: 256
-  - Max Bucket Resolution: 4096
-- Other
-  - Caption Tag Dropout: 0.2
-  - Caption Group Dropout: 0.2 (for dropping tag/nl caption entirely)
 
 
 ## Why do you still use SDXL but not any Brand New DiT-Based Models?