Model card auto-generated by SimpleTuner

README.md

@@ -18,7 +18,7 @@ widget:
     negative_prompt: 'blurry, cropped, ugly'
   output:
     url: ./assets/image_0_0.png
-- text: 'a lighthouse'
+- text: 'a lighthouse ani_style'
   parameters:
     negative_prompt: 'blurry, cropped, ugly'
   output:
@@ -35,7 +35,7 @@ The main validation prompt used during training was:
 
 
 ```
-a lighthouse
+a lighthouse ani_style
 ```
 
 ## Validation settings
@@ -59,8 +59,8 @@ You may reuse the base model text encoder for inference.
 
 ## Training settings
 
-- Training epochs: 145
-- Training steps: 1750
+- Training epochs: 20
+- Training steps: 250
 - Learning rate: 0.0001
 - Effective batch size: 1
   - Micro-batch size: 1
@@ -102,7 +102,7 @@ adapter_id = 'vheretic/testing-flux'
 pipeline = DiffusionPipeline.from_pretrained(model_id)
 pipeline.load_lora_weights(adapter_id)
 
-prompt = "a lighthouse"
+prompt = "a lighthouse ani_style"
 
 pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu')
 image = pipeline(