diff --git a/README.md b/README.md
index f0ee750..43cc224 100644
--- a/README.md
+++ b/README.md
@@ -197,7 +197,7 @@ Note: This method supports only the mask type of text prompt.
 
 After running our demo code, you can get the tracking results as follows:
 
-[![Video Name](./assets/tracking_car_mask_1.jpg)](https://github.com/user-attachments/assets/d4b80e9b-bab3-4562-8b1a-9bf41e454b68)
+[![Video Name](./assets/tracking_car_mask_1.jpg)](https://github.com/user-attachments/assets/d3f91ad0-3d32-43c4-a0dc-0bed661415f4)
 
 ### Citation
 
diff --git a/grounded_sam2_tracking_demo_with_continuous_id.py b/grounded_sam2_tracking_demo_with_continuous_id.py
index ab2e0c2..4431a54 100644
--- a/grounded_sam2_tracking_demo_with_continuous_id.py
+++ b/grounded_sam2_tracking_demo_with_continuous_id.py
@@ -68,7 +68,7 @@ frame_names.sort(key=lambda p: int(os.path.splitext(p)[0]))
 
 # init video predictor state
 inference_state = video_predictor.init_state(video_path=video_dir)
-step = 25 # the step to sample frames for Grounding DINO predictor
+step = 10 # the step to sample frames for Grounding DINO predictor
 
 sam2_masks = MaskDictionatyModel()
 PROMPT_TYPE_FOR_VIDEO = "mask" # box, mask or point