Update app.py

app.py

@@ -411,7 +411,9 @@ def bot(history, temperature, top_p, max_output_tokens):
                         dst.write(src.read())
     
     image_tensor = []
-    if not is_video:
+    if is_video:
+        image_tensor = our_chatbot.image_processor.preprocess(image_list, return_tensors="pt")["pixel_values"].half().to(our_chatbot.model.device)
+    elif num_new_images > 0:
         image_tensor = [
             our_chatbot.image_processor.preprocess(f, return_tensors="pt")["pixel_values"][
                 0
@@ -421,9 +423,6 @@ def bot(history, temperature, top_p, max_output_tokens):
             for f in image_list
         ]
         image_tensor = torch.stack(image_tensor)
-    elif num_new_images > 0:
-        image_tensor = our_chatbot.image_processor.preprocess(image_list, return_tensors="pt")["pixel_values"].half().to(our_chatbot.model.device)
-    
     
     image_token = DEFAULT_IMAGE_TOKEN * num_new_images + "\n"
     
@@ -659,7 +658,7 @@ with gr.Blocks(
                 [
                     {
                         "files": [
-                            f"{cur_dir}/examples/realcase_video.mp4",
+                            f"{cur_dir}/examples/realcase_video.jpg",
                         ],
                         "text": "Please describe the video in detail.",
                     },