Update app.py

app.py

@@ -60,7 +60,7 @@ def generate_caption_and_image(image):
 
     pixel_values = feature_extractor(images=[img], return_tensors="pt").pixel_values.to(device)
     output_ids = model.generate(pixel_values, **gen_kwargs)
-    caption = tokenizer.decode(output_ids[0], skip_special_tokens=True).strip()
+    caption1 = tokenizer.decode(output_ids[0], skip_special_tokens=True).strip()