Update README.md

README.md

@@ -198,7 +198,8 @@ video,frame_time,video_time = load_video(video_path, max_frames_num, 1, force_sa
 video = image_processor.preprocess(video, return_tensors="pt")["pixel_values"].cuda().bfloat16()
 video = [video]
 conv_template = "qwen_1_5"  # Make sure you use correct chat template for different models
-question = DEFAULT_IMAGE_TOKEN + "\nPlease describe this video in detail."
+time_instruciton = f"The video lasts for {video_time:.2f} seconds, and {len(video[0])} frames are uniformly sampled from it. These frames are located at {frame_time}.Please answer the following questions related to this video."
+question = DEFAULT_IMAGE_TOKEN + f"{time_instruciton}\nPlease describe this video in detail."
 conv = copy.deepcopy(conv_templates[conv_template])
 conv.append_message(conv.roles[0], question)
 conv.append_message(conv.roles[1], None)