Update app.py

app.py

@@ -1,20 +1,26 @@
 import gradio as gr
 import requests
-from transformers import pipeline
+from PIL import Image
+from transformers import BlipProcessor, BlipForConditionalGeneration
+
+processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
+model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large")
 
-# Create a Gradio interface
 def caption_image(input_image):
-   
-    caption_model_url = "Salesforce/blip-image-captioning-large" 
-    files = {"file": open(input_image.name, "rb")}
-    response = requests.post(caption_model_url, files=files)
-    caption = response.json()["caption"]
+    raw_image = Image.open(input_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)
     
-    # Use the Transformers pipeline for sentiment analysis
-    sentiment_model = pipeline("sentiment-analysis")
-    sentiment_score = sentiment_model(caption)[0]["label"]
+    # Unconditional image captioning
+    inputs = processor(raw_image, return_tensors="pt")
+    out = model.generate(**inputs)
+    caption_unconditional = processor.decode(out[0], skip_special_tokens=True)
     
-    return f"Caption: {caption}\nSentiment: {sentiment_score}"
+    return f"Conditional Caption: {caption_conditional}\nUnconditional Caption: {caption_unconditional}"
 
 # Define the Gradio input interface
 inputs = gr.inputs.Image()