Update app.py

app.py

@@ -96,7 +96,7 @@ def inference(
     elif task == "audio-text":
         result = audio_text_zeroshot(audio, text_list)
     elif task == "video-text":
-        result = video_text_zeroshot(image2, text_list)
+        result = video_text_zeroshot(image, text_list)
     else:
         raise NotImplementedError
     return result
@@ -117,7 +117,7 @@ def main():
         gr.inputs.Textbox(lines=1, label="Candidate texts"),
         gr.inputs.Image(type="filepath", label="Input image"),
         gr.inputs.Audio(type="filepath", label="Input audio"),
-         gr.inputs.Image(type="filepath", label="Input image"),
+         gr.inputs.Image(type="filepath", label="Input image2"),
     ]
 
     iface = gr.Interface(