Update app.py

app.py

@@ -40,6 +40,21 @@ model.eval()
 device = "cuda" if torch.cuda.is_available() else "cpu"
 model.to(device)
 
+# Function to generate captions dynamically based on image content
+def generate_captions_from_image(image):
+    if image.mode != "RGB":
+        image = image.convert("RGB")
+    
+    # Resize image for faster processing
+    image = image.resize((640, 640))
+    
+    # Preprocess the image and generate a caption
+    inputs = processor(image, return_tensors="pt").to(device, torch.float16)
+    output = model.generate(**inputs, max_new_tokens=50)
+    caption = processor.decode(output[0], skip_special_tokens=True)
+    
+    return caption
+
 # FastAPI endpoint to handle image upload and forward it to Hugging Face API for caption generation
 HUGGING_FACE_ENDPOINT = 'https://huggingface.co/spaces/Rammohan0504/DPR-4/predict'
 
@@ -262,8 +277,6 @@ iface = gr.Interface(
     allow_flagging="never"
 )
 
-
-
 if __name__ == "__main__":
         iface.launch()