Model card auto-generated by SimpleTuner

README.md

@@ -10,17 +10,7 @@ tags:
   - lora
   - template:sd-lora
 inference: true
-widget:
-- text: 'unconditional (blank prompt)'
-  parameters:
-    negative_prompt: 'blurry, cropped, ugly, creature'
-  output:
-    url: ./assets/image_0_0.png
-- text: 'e4g4, A pet egg wrapped in moss and plant essence, resembling a Pokémon game item, on a white background, in the style of Ken Sugimori vector art.'
-  parameters:
-    negative_prompt: 'blurry, cropped, ugly, creature'
-  output:
-    url: ./assets/image_1_0.png
+
 ---
 
 # sd3_egg_lora_rank32_v1
@@ -46,7 +36,7 @@ e4g4, A pet egg wrapped in moss and plant essence, resembling a Pokémon game it
 
 Note: The validation settings are not necessarily the same as the [training settings](#training-settings).
 
-You can find some example images in the following gallery:
+
 
 
 <Gallery />
@@ -58,8 +48,8 @@ You may reuse the base model text encoder for inference.
 ## Training settings
 
 - Training epochs: 41
-- Training steps: 3000
-- Learning rate: 0.0001
+- Training steps: 3001
+- Learning rate: 8e-05
 - Effective batch size: 1
   - Micro-batch size: 1
   - Gradient accumulation steps: 1
@@ -101,7 +91,7 @@ pipeline = DiffusionPipeline.from_pretrained(model_id)
 pipeline.load_lora_weights(adapter_id)
 
 prompt = "e4g4, A pet egg wrapped in moss and plant essence, resembling a Pokémon game item, on a white background, in the style of Ken Sugimori vector art."
-negative_prompt = 'blurry, cropped, ugly, creature'
+negative_prompt = 'blurry, cropped, ugly, eyes'
 pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu')
 image = pipeline(
     prompt=prompt,