Model card auto-generated by SimpleTuner

README.md

@@ -13,12 +13,12 @@ inference: true
 widget:
 - text: 'unconditional (blank prompt)'
   parameters:
-    negative_prompt: 'blurry, cropped, ugly'
+    negative_prompt: ''''
   output:
     url: ./assets/image_0_0.png
 - text: 'Emily a anthropomorphic shark blue body short blue haired girl black eye patch red eyes wearing armour and a long red cape'
   parameters:
-    negative_prompt: 'blurry, cropped, ugly'
+    negative_prompt: ''''
   output:
     url: ./assets/image_1_0.png
 ---
@@ -58,11 +58,11 @@ You may reuse the base model text encoder for inference.
 
 ## Training settings
 
-- Training epochs: 13
-- Training steps: 200
+- Training epochs: 3
+- Training steps: 100
 - Learning rate: 8e-07
-- Effective batch size: 2
-  - Micro-batch size: 2
+- Effective batch size: 1
+  - Micro-batch size: 1
   - Gradient accumulation steps: 1
   - Number of GPUs: 1
 - Prediction type: flow-matching