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'
-  output:
-    url: ./assets/image_0_0.png
-- text: 'A design of a cute pokemon, on a white background'
-  parameters:
-    negative_prompt: 'blurry, cropped, ugly'
-  output:
-    url: ./assets/image_1_0.png
+
 ---
 
 # sd3-lora-training-v2
@@ -33,7 +23,7 @@ The main validation prompt used during training was:
 
 
 ```
-A design of a cute pokemon, on a white background
+ethnographic photography of teddy bear at a picnic
 ```
 
 ## Validation settings
@@ -46,7 +36,7 @@ A design of a cute pokemon, on a white background
 
 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 />
@@ -57,9 +47,9 @@ You may reuse the base model text encoder for inference.
 
 ## Training settings
 
-- Training epochs: 90
-- Training steps: 3000
-- Learning rate: 0.0001
+- Training epochs: 89
+- Training steps: 2960
+- Learning rate: 8e-07
 - Effective batch size: 2
   - Micro-batch size: 1
   - Gradient accumulation steps: 2
@@ -80,7 +70,7 @@ You may reuse the base model text encoder for inference.
 
 ### Pal_BLIP
 - Repeats: 0
-- Total number of images: 66
+- Total number of images: 73
 - Total number of aspect buckets: 1
 - Resolution: 1.048576 megapixels
 - Cropped: True
@@ -100,7 +90,7 @@ adapter_id = 'zwloong/sd3-lora-training-v2'
 pipeline = DiffusionPipeline.from_pretrained(model_id)
 pipeline.load_lora_weights(adapter_id)
 
-prompt = "A design of a cute pokemon, on a white background"
+prompt = "ethnographic photography of teddy bear at a picnic"
 negative_prompt = 'blurry, cropped, ugly'
 pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu')
 image = pipeline(