Update app.py

app.py

@@ -25,7 +25,7 @@ parser.add_argument('--image_caption', action='store_true', dest='image_caption'
 parser.add_argument('--dense_caption', action='store_true', dest='dense_caption', default=True, help='Set this flag to True if you want to use Dense Caption')
 parser.add_argument('--feature_extractor', default='openai/clip-vit-base-patch32', help='Select the feature extractor model for video segmentation')
 parser.add_argument('--feature_extractor_device', choices=['cuda', 'cpu'], default='cuda', help='Select the device: cuda or cpu')
-parser.add_argument('--image_captioner', choices=['blip2', 'blip2-opt'], dest='captioner_base_model', default='blip2', help='blip2 requires 15G GPU memory, blip requires 6G GPU memory')
+parser.add_argument('--image_captioner', choices=['blip2', 'blip2-opt'], dest='captioner_base_model', default='blip2-opt', help='blip2 requires 15G GPU memory, blip requires 6G GPU memory')
 parser.add_argument('--image_captioner_device', choices=['cuda', 'cpu'], default='cuda', help='Select the device: cuda or cpu, gpu memory larger than 14G is recommended')
 parser.add_argument('--dense_captioner_device', choices=['cuda', 'cpu'], default='cuda', help='Select the device: cuda or cpu, < 6G GPU is not recommended>')
 parser.add_argument('--audio_translator', default='large')