Update app.py

app.py

@@ -3,28 +3,24 @@ import requests
 from PIL import Image
 from transformers import BlipProcessor, BlipForConditionalGeneration
 
+# Load BLIP model
 processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
 model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large")
 
-def caption_image(input_image):
-    raw_image = Image.open(input_image).convert('RGB')
+# Define function for generating captions
+def generate_caption(image):
+    # Convert image to PIL format
+    raw_image = Image.open(image).convert('RGB')
     
-    # Conditional image captioning
-    text = "a photography of"
-    inputs = processor(raw_image, text, return_tensors="pt")
-    out = model.generate(**inputs)
-    caption_conditional = processor.decode(out[0], skip_special_tokens=True)
-    
-    # Unconditional image captioning
+    # Preprocess the image and generate caption
     inputs = processor(raw_image, return_tensors="pt")
     out = model.generate(**inputs)
-    caption_unconditional = processor.decode(out[0], skip_special_tokens=True)
+    caption = processor.decode(out[0], skip_special_tokens=True)
     
-    return f"Conditional Caption: {caption_conditional}\nUnconditional Caption: {caption_unconditional}"
+    return caption
 
-# Define the Gradio input interface
-inputs = gr.inputs.Image()
-output = gr.outputs.Textbox()
+# Create Gradio interface
+image_input = gr.inputs.Image()
+caption_output = gr.outputs.Textbox()
 
-# Launch the Gradio app
-gr.Interface(fn=caption_image, inputs=inputs, outputs=output, live=True).launch()
+gr.Interface(fn=generate_caption, inputs=image_input, outputs=caption_output).launch()