Update app.py

app.py

@@ -21,7 +21,8 @@ def generate_caption(image):
     if not isinstance(image, Image.Image):
         image = Image.fromarray(image)
     
-    inputs = florence_processor(text="<MORE_DETAILED_CAPTION>", images=image, return_tensors="pt").to(device)
+    inputs = florence_processor(text="<MORE_DETAILED_CAPTION>", images=image, return_tensors="pt")
+    inputs = {k: v.to(device) for k, v in inputs.items()}
     generated_ids = florence_model.generate(
         input_ids=inputs["input_ids"],
         pixel_values=inputs["pixel_values"],