Model card auto-generated by SimpleTuner

README.md

@@ -16,7 +16,7 @@ widget:
     negative_prompt: 'blurry, cropped, ugly'
   output:
     url: ./assets/image_0_0.png
-- text: 'a photo of distracted boyfriend meme'
+- text: 'a photo of a man'
   parameters:
     negative_prompt: 'blurry, cropped, ugly'
   output:
@@ -34,7 +34,7 @@ The main validation prompt used during training was:
 
 
 ```
-a photo of distracted boyfriend meme
+a photo of a man
 ```
 
 ## Validation settings
@@ -58,8 +58,8 @@ You may reuse the base model text encoder for inference.
 
 ## Training settings
 
-- Training epochs: 1999
-- Training steps: 2000
+- Training epochs: 96
+- Training steps: 2522
 - Learning rate: 0.0001
 - Effective batch size: 1
   - Micro-batch size: 1
@@ -81,12 +81,12 @@ You may reuse the base model text encoder for inference.
 
 ### meme1
 - Repeats: 0
-- Total number of images: 1
+- Total number of images: 26
 - Total number of aspect buckets: 1
-- Resolution: 512 px
-- Cropped: True
-- Crop style: center
-- Crop aspect: square
+- Resolution: 1024 px
+- Cropped: False
+- Crop style: None
+- Crop aspect: None
 
 
 ## Inference
@@ -101,7 +101,7 @@ adapter_id = 'ambientocclusion/meme1'
 pipeline = DiffusionPipeline.from_pretrained(model_id)
 pipeline.load_lora_weights(adapter_id)
 
-prompt = "a photo of distracted boyfriend meme"
+prompt = "a photo of a man"
 
 
 pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu')