Model card auto-generated by SimpleTuner

README.md

@@ -18,12 +18,12 @@ widget:
     negative_prompt: 'blurry, cropped, ugly'
   output:
     url: ./assets/image_0_0.png
-- text: 'a photo of a woman'
+- text: 'a photo of a nude woman'
   parameters:
     negative_prompt: 'blurry, cropped, ugly'
   output:
     url: ./assets/image_1_0.png
-- text: 'a photo of a woman, nsfw'
+- text: 'a photo of a nude woman, nsfw'
   parameters:
     negative_prompt: 'blurry, cropped, ugly'
   output:
@@ -40,7 +40,7 @@ The main validation prompt used during training was:
 
 
 ```
-a photo of a woman, nsfw
+a photo of a nude woman, nsfw
 ```
 
 ## Validation settings
@@ -65,7 +65,7 @@ You may reuse the base model text encoder for inference.
 ## Training settings
 
 - Training epochs: 0
-- Training steps: 1900
+- Training steps: 100
 - Learning rate: 0.0001
 - Effective batch size: 4
   - Micro-batch size: 1
@@ -87,7 +87,7 @@ You may reuse the base model text encoder for inference.
 
 ### dreambooth-512
 - Repeats: 0
-- Total number of images: 4289
+- Total number of images: 3984
 - Total number of aspect buckets: 1
 - Resolution: 0.262144 megapixels
 - Cropped: False
@@ -95,7 +95,7 @@ You may reuse the base model text encoder for inference.
 - Crop aspect: None
 ### dreambooth-768
 - Repeats: 0
-- Total number of images: 4289
+- Total number of images: 3984
 - Total number of aspect buckets: 1
 - Resolution: 0.589824 megapixels
 - Cropped: False
@@ -103,7 +103,7 @@ You may reuse the base model text encoder for inference.
 - Crop aspect: None
 ### dreambooth-1024
 - Repeats: 0
-- Total number of images: 4289
+- Total number of images: 3984
 - Total number of aspect buckets: 1
 - Resolution: 1.048576 megapixels
 - Cropped: False
@@ -111,7 +111,7 @@ You may reuse the base model text encoder for inference.
 - Crop aspect: None
 ### dreambooth-512-crop
 - Repeats: 0
-- Total number of images: 4289
+- Total number of images: 3984
 - Total number of aspect buckets: 1
 - Resolution: 0.262144 megapixels
 - Cropped: True
@@ -119,7 +119,7 @@ You may reuse the base model text encoder for inference.
 - Crop aspect: square
 ### dreambooth-768-crop
 - Repeats: 0
-- Total number of images: 4289
+- Total number of images: 3984
 - Total number of aspect buckets: 1
 - Resolution: 0.589824 megapixels
 - Cropped: True
@@ -127,7 +127,7 @@ You may reuse the base model text encoder for inference.
 - Crop aspect: square
 ### dreambooth-1024-crop
 - Repeats: 0
-- Total number of images: 4289
+- Total number of images: 3984
 - Total number of aspect buckets: 1
 - Resolution: 1.048576 megapixels
 - Cropped: True
@@ -147,7 +147,7 @@ adapter_id = 'tungdop2/nsfw-1024-id-only'
 pipeline = DiffusionPipeline.from_pretrained(model_id)
 pipeline.load_lora_weights(adapter_id)
 
-prompt = "a photo of a woman, nsfw"
+prompt = "a photo of a nude woman, nsfw"
 
 pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu')
 image = pipeline(