Update app.py

app.py

@@ -86,6 +86,9 @@ def generate_caption(image):
 
         inputs = florence_processor(text=prompt, images=image, return_tensors="pt").to(device)
         
+        # Cast floating-point inputs to match model's dtype (float16)
+        inputs["pixel_values"] = inputs["pixel_values"].to(torch.float16)
+        
         generated_ids = florence_model.generate(
             input_ids=inputs["input_ids"],
             pixel_values=inputs["pixel_values"],