nits

sam2/sam2_video_predictor.py

@@ -590,7 +590,7 @@ def propagate_in_video_preflight(self, inference_state):
             storage_key = "cond_frame_outputs" if is_cond else "non_cond_frame_outputs"
             # Find all the frames that contain temporary outputs for any objects
             # (these should be the frames that have just received clicks for mask inputs
-            # via `add_new_points` or `add_new_mask`)
+            # via `add_new_points_or_box` or `add_new_mask`)
             temp_frame_inds = set()
             for obj_temp_output_dict in temp_output_dict_per_obj.values():
                 temp_frame_inds.update(obj_temp_output_dict[storage_key].keys())