Add model auto-download and troubleshooting instructions

README.md

@@ -9,6 +9,14 @@ app_file: app.py
 pinned: false
 ---
 
+# ⚠️ IMPORTANT SETUP STEP
+**If you see "Welcome to your static Space"**:
+1. Go to the **Settings** tab above.
+2. Scroll to **Select Space SDK**.
+3. Change it from **Static** to **Docker**.
+4. Click **Update Space**.
+The app will then build and start!
+
 # 🎥 MotionScope Pro — Movement Detector
 
 A professional Streamlit application combining **MediaPipe hand tracking** and **background subtraction motion detection**.

detector.py

@@ -4,6 +4,7 @@ Combines MediaPipe HandLandmarker (tasks API) with background subtraction.
 """
 
 import os
+import urllib.request
 import cv2
 import numpy as np
 import mediapipe as mp
@@ -21,6 +22,15 @@ _RunningMode = mp.tasks.vision.RunningMode
 _MODEL_PATH = os.path.join(os.path.dirname(__file__), "hand_landmarker.task")
 
 
+def _ensure_model_exists():
+    """Download the model if it doesn't exist locally."""
+    if not os.path.exists(_MODEL_PATH):
+        print(f"Downloading model to {_MODEL_PATH}...")
+        url = "https://storage.googleapis.com/mediapipe-models/hand_landmarker/hand_landmarker/float16/latest/hand_landmarker.task"
+        urllib.request.urlretrieve(url, _MODEL_PATH)
+
+
+
 class DetectionMode(Enum):
     """Available detection modes."""
     HAND_TRACKING = "Hand Tracking"
@@ -65,6 +75,7 @@ class MovementDetector:
     # ------------------------------------------------------------------
 
     def _build_hand_landmarker(self):
+        _ensure_model_exists()
         options = _HandLandmarkerOptions(
             base_options=_BaseOptions(model_asset_path=_MODEL_PATH),
             running_mode=_RunningMode.IMAGE,