Updated with OCR model and Gradio integration

app.py

@@ -20,7 +20,24 @@ model.to(device)
 def analyze_image(image):
     try:
         img = image.convert("RGB")
-        inputs = processor(images=img, text="describe this image", return_tensors="pt").to(device)
+        
+        # Process the image
+        image_inputs = processor(images=img, return_tensors="pt")
+        # Process the text
+        text_inputs = tokenizer("describe this image", return_tensors="pt")
+        
+        # Move inputs to the appropriate device
+        image_inputs = {k: v.to(device) for k, v in image_inputs.items()}
+        text_inputs = {k: v.to(device) for k, v in text_inputs.items()}
+        
+        # Combine the inputs
+        inputs = {
+            "input_ids": text_inputs["input_ids"],
+            "attention_mask": text_inputs["attention_mask"],
+            "pixel_values": image_inputs["pixel_values"],
+        }
+        
+        # Generate outputs
         outputs = model.generate(**inputs)
         return tokenizer.decode(outputs[0], skip_special_tokens=True)
     except Exception as e:
@@ -35,4 +52,4 @@ demo = gr.Interface(
 )
 
 if __name__ == "__main__":
-    demo.launch(share=True)
+    demo.launch()