fix(passport-photo): use bg-background for dropdown to match app theme

packages/ai/python/detect_faces.py

@@ -1,6 +1,7 @@
 """Face detection and blurring using MediaPipe."""
 import sys
 import json
+import os
 
 
 def emit_progress(percent, stage):
@@ -8,6 +9,92 @@ def emit_progress(percent, stage):
     print(json.dumps({"progress": percent, "stage": stage}), file=sys.stderr, flush=True)
 
 
+# ── Model path for new mp.tasks API ─────────────────────────────────
+
+_FACE_DETECT_MODEL_URL = "https://storage.googleapis.com/mediapipe-models/face_detector/blaze_face_short_range/float16/latest/blaze_face_short_range.task"
+_MODEL_DIR = os.path.join(os.path.dirname(__file__), "..", "..", "..", ".models")
+_FACE_DETECT_MODEL_PATH = os.path.join(_MODEL_DIR, "blaze_face_short_range.task")
+
+
+def _ensure_face_detect_model():
+    """Download the face detector model if not present."""
+    if os.path.exists(_FACE_DETECT_MODEL_PATH):
+        return _FACE_DETECT_MODEL_PATH
+    os.makedirs(_MODEL_DIR, exist_ok=True)
+    import urllib.request
+    emit_progress(15, "Downloading face detection model")
+    urllib.request.urlretrieve(_FACE_DETECT_MODEL_URL, _FACE_DETECT_MODEL_PATH)
+    return _FACE_DETECT_MODEL_PATH
+
+
+def _detect_with_solutions(img_array, min_confidence):
+    """Detect faces using legacy mp.solutions API (mediapipe < 0.10.30)."""
+    import mediapipe as mp
+
+    mp_face = mp.solutions.face_detection
+    results = None
+    for model_sel in [0, 1]:
+        detector = mp_face.FaceDetection(
+            model_selection=model_sel,
+            min_detection_confidence=min_confidence,
+        )
+        results = detector.process(img_array)
+        detector.close()
+        if results.detections:
+            break
+
+    detections = results.detections or []
+    if not detections:
+        return []
+
+    ih, iw = img_array.shape[:2]
+    faces = []
+    for detection in detections:
+        bbox = detection.location_data.relative_bounding_box
+        faces.append({
+            "x": int(bbox.xmin * iw),
+            "y": int(bbox.ymin * ih),
+            "w": int(bbox.width * iw),
+            "h": int(bbox.height * ih),
+        })
+    return faces
+
+
+def _detect_with_tasks(img_array, min_confidence):
+    """Detect faces using new mp.tasks API (mediapipe >= 0.10.30)."""
+    import mediapipe as mp
+
+    model_path = _ensure_face_detect_model()
+    options = mp.tasks.vision.FaceDetectorOptions(
+        base_options=mp.tasks.BaseOptions(model_asset_path=model_path),
+        running_mode=mp.tasks.vision.RunningMode.IMAGE,
+        min_detection_confidence=min_confidence,
+    )
+    detector = mp.tasks.vision.FaceDetector.create_from_options(options)
+    mp_image = mp.Image(image_format=mp.ImageFormat.SRGB, data=img_array)
+    result = detector.detect(mp_image)
+    detector.close()
+
+    faces = []
+    for detection in result.detections:
+        bbox = detection.bounding_box
+        faces.append({
+            "x": bbox.origin_x,
+            "y": bbox.origin_y,
+            "w": bbox.width,
+            "h": bbox.height,
+        })
+    return faces
+
+
+def _detect_faces(img_array, min_confidence):
+    """Detect faces, trying legacy API first then falling back to tasks API."""
+    try:
+        return _detect_with_solutions(img_array, min_confidence)
+    except AttributeError:
+        return _detect_with_tasks(img_array, min_confidence)
+
+
 def main():
     input_path = sys.argv[1]
     output_path = sys.argv[2]
@@ -24,7 +111,6 @@ def main():
         img = Image.open(input_path).convert("RGB")
 
         try:
-            import mediapipe as mp
             import numpy as np
 
             emit_progress(20, "Ready")
@@ -34,56 +120,33 @@ def main():
             min_confidence = max(0.1, 1.0 - sensitivity)
 
             img_array = np.array(img)
-            mp_face = mp.solutions.face_detection
 
-            # Try short-range model first (model_selection=0, best for faces
-            # within ~2m which covers most photos), then fall back to
-            # full-range model (model_selection=1) for distant/group shots.
+            # Try legacy mp.solutions API first, fall back to mp.tasks
             emit_progress(25, "Scanning for faces")
-            results = None
-            for model_sel in [0, 1]:
-                detector = mp_face.FaceDetection(
-                    model_selection=model_sel,
-                    min_detection_confidence=min_confidence,
-                )
-                results = detector.process(img_array)
-                detector.close()
-                if results.detections:
-                    break
-
-            faces = []
-            detections = results.detections or []
-            num_faces = len(detections)
+            faces = _detect_faces(img_array, min_confidence)
+            num_faces = len(faces)
             emit_progress(50, f"Found {num_faces} face{'s' if num_faces != 1 else ''}")
 
-            if num_faces > 0:
-                ih, iw = img_array.shape[:2]
-                for i, detection in enumerate(detections):
-                    bbox = detection.location_data.relative_bounding_box
-                    x = int(bbox.xmin * iw)
-                    y = int(bbox.ymin * ih)
-                    w = int(bbox.width * iw)
-                    h = int(bbox.height * ih)
+            if num_faces > 0 and not detect_only:
+                for i, face in enumerate(faces):
+                    x, y, w, h = face["x"], face["y"], face["w"], face["h"]
 
-                    if not detect_only:
-                        # Add padding around the face
-                        pad = int(max(w, h) * 0.1)
-                        x1 = max(0, x - pad)
-                        y1 = max(0, y - pad)
-                        x2 = min(img.width, x + w + pad)
-                        y2 = min(img.height, y + h + pad)
+                    # Add padding around the face
+                    pad = int(max(w, h) * 0.1)
+                    x1 = max(0, x - pad)
+                    y1 = max(0, y - pad)
+                    x2 = min(img.width, x + w + pad)
+                    y2 = min(img.height, y + h + pad)
 
-                        face_region = img.crop((x1, y1, x2, y2))
-                        blurred = face_region.filter(
-                            ImageFilter.GaussianBlur(blur_radius)
-                        )
-                        img.paste(blurred, (x1, y1))
-                        emit_progress(
-                            50 + int((i + 1) / num_faces * 40),
-                            f"Blurring face {i + 1} of {num_faces}",
-                        )
-
-                    faces.append({"x": x, "y": y, "w": w, "h": h})
+                    face_region = img.crop((x1, y1, x2, y2))
+                    blurred = face_region.filter(
+                        ImageFilter.GaussianBlur(blur_radius)
+                    )
+                    img.paste(blurred, (x1, y1))
+                    emit_progress(
+                        50 + int((i + 1) / num_faces * 40),
+                        f"Blurring face {i + 1} of {num_faces}",
+                    )
 
             if not detect_only:
                 emit_progress(95, "Saving result")

packages/ai/python/enhance_faces.py

@@ -37,45 +37,90 @@ CODEFORMER_MODEL_PATH = os.environ.get(
 )
 
 
+# ── Model path for new mp.tasks API ─────────────────────────────────
+
+_FACE_DETECT_MODEL_URL = "https://storage.googleapis.com/mediapipe-models/face_detector/blaze_face_short_range/float16/latest/blaze_face_short_range.task"
+_MODEL_DIR = os.path.join(os.path.dirname(__file__), "..", "..", "..", ".models")
+_FACE_DETECT_MODEL_PATH = os.path.join(_MODEL_DIR, "blaze_face_short_range.task")
+
+
+def _ensure_face_detect_model():
+    """Download the face detector model if not present."""
+    if os.path.exists(_FACE_DETECT_MODEL_PATH):
+        return _FACE_DETECT_MODEL_PATH
+    os.makedirs(_MODEL_DIR, exist_ok=True)
+    import urllib.request
+    emit_progress(15, "Downloading face detection model")
+    urllib.request.urlretrieve(_FACE_DETECT_MODEL_URL, _FACE_DETECT_MODEL_PATH)
+    return _FACE_DETECT_MODEL_PATH
+
+
 def detect_faces_mediapipe(img_array, sensitivity):
     """Detect faces using MediaPipe with dual-model approach.
 
     Returns a list of {x, y, w, h} dicts for each detected face.
+    Tries legacy mp.solutions API first, falls back to mp.tasks.
     """
     import mediapipe as mp
 
     min_confidence = max(0.1, 1.0 - sensitivity)
-    mp_face = mp.solutions.face_detection
 
-    # Try short-range model first (model_selection=0, best for faces
-    # within ~2m which covers most photos), then fall back to
-    # full-range model (model_selection=1) for distant/group shots.
-    detections = []
-    for model_sel in [0, 1]:
-        detector = mp_face.FaceDetection(
-            model_selection=model_sel,
+    try:
+        mp_face = mp.solutions.face_detection
+
+        # Try short-range model first (model_selection=0, best for faces
+        # within ~2m which covers most photos), then fall back to
+        # full-range model (model_selection=1) for distant/group shots.
+        detections = []
+        for model_sel in [0, 1]:
+            detector = mp_face.FaceDetection(
+                model_selection=model_sel,
+                min_detection_confidence=min_confidence,
+            )
+            results = detector.process(img_array)
+            detector.close()
+            if results.detections:
+                detections = results.detections
+                break
+
+        if not detections:
+            return []
+
+        ih, iw = img_array.shape[:2]
+        faces = []
+        for detection in detections:
+            bbox = detection.location_data.relative_bounding_box
+            faces.append({
+                "x": int(bbox.xmin * iw),
+                "y": int(bbox.ymin * ih),
+                "w": int(bbox.width * iw),
+                "h": int(bbox.height * ih),
+            })
+        return faces
+
+    except AttributeError:
+        # mediapipe >= 0.10.30 removed mp.solutions, use tasks API
+        model_path = _ensure_face_detect_model()
+        options = mp.tasks.vision.FaceDetectorOptions(
+            base_options=mp.tasks.BaseOptions(model_asset_path=model_path),
+            running_mode=mp.tasks.vision.RunningMode.IMAGE,
             min_detection_confidence=min_confidence,
         )
-        results = detector.process(img_array)
+        detector = mp.tasks.vision.FaceDetector.create_from_options(options)
+        mp_image = mp.Image(image_format=mp.ImageFormat.SRGB, data=img_array)
+        result = detector.detect(mp_image)
         detector.close()
-        if results.detections:
-            detections = results.detections
-            break
 
-    if not detections:
-        return []
-
-    ih, iw = img_array.shape[:2]
-    faces = []
-    for detection in detections:
-        bbox = detection.location_data.relative_bounding_box
-        x = int(bbox.xmin * iw)
-        y = int(bbox.ymin * ih)
-        w = int(bbox.width * iw)
-        h = int(bbox.height * ih)
-        faces.append({"x": x, "y": y, "w": w, "h": h})
-
-    return faces
+        faces = []
+        for detection in result.detections:
+            bbox = detection.bounding_box
+            faces.append({
+                "x": bbox.origin_x,
+                "y": bbox.origin_y,
+                "w": bbox.width,
+                "h": bbox.height,
+            })
+        return faces
 
 
 def enhance_with_gfpgan(img_array, only_center_face):

packages/ai/python/red_eye_removal.py

@@ -9,6 +9,79 @@ def emit_progress(percent, stage):
     print(json.dumps({"progress": percent, "stage": stage}), file=sys.stderr, flush=True)
 
 
+# ── Model path for new mp.tasks API ─────────────────────────────────
+
+_FACE_MESH_MODEL_URL = "https://storage.googleapis.com/mediapipe-models/face_landmarker/face_landmarker/float16/latest/face_landmarker.task"
+_MODEL_DIR = os.path.join(os.path.dirname(__file__), "..", "..", "..", ".models")
+_FACE_MESH_MODEL_PATH = os.path.join(_MODEL_DIR, "face_landmarker.task")
+
+
+def _ensure_face_mesh_model():
+    """Download the face landmarker model if not present."""
+    if os.path.exists(_FACE_MESH_MODEL_PATH):
+        return _FACE_MESH_MODEL_PATH
+    os.makedirs(_MODEL_DIR, exist_ok=True)
+    import urllib.request
+    emit_progress(15, "Downloading face mesh model")
+    urllib.request.urlretrieve(_FACE_MESH_MODEL_URL, _FACE_MESH_MODEL_PATH)
+    return _FACE_MESH_MODEL_PATH
+
+
+def _mesh_with_solutions(img_array, max_faces=10, min_confidence=0.5):
+    """FaceMesh using legacy mp.solutions API (mediapipe < 0.10.30).
+
+    Returns list of landmark lists. Each landmark has .x, .y attributes.
+    """
+    import mediapipe as mp
+
+    mesh = mp.solutions.face_mesh.FaceMesh(
+        static_image_mode=True,
+        max_num_faces=max_faces,
+        refine_landmarks=True,
+        min_detection_confidence=min_confidence,
+    )
+    results = mesh.process(img_array)
+    mesh.close()
+
+    if not results.multi_face_landmarks:
+        return []
+
+    return [face.landmark for face in results.multi_face_landmarks]
+
+
+def _mesh_with_tasks(img_array, max_faces=10, min_confidence=0.5):
+    """FaceMesh using new mp.tasks API (mediapipe >= 0.10.30).
+
+    Returns list of landmark lists. Each landmark has .x, .y attributes.
+    """
+    import mediapipe as mp
+
+    model_path = _ensure_face_mesh_model()
+    options = mp.tasks.vision.FaceLandmarkerOptions(
+        base_options=mp.tasks.BaseOptions(model_asset_path=model_path),
+        running_mode=mp.tasks.vision.RunningMode.IMAGE,
+        num_faces=max_faces,
+        min_face_detection_confidence=min_confidence,
+    )
+    landmarker = mp.tasks.vision.FaceLandmarker.create_from_options(options)
+    mp_image = mp.Image(image_format=mp.ImageFormat.SRGB, data=img_array)
+    result = landmarker.detect(mp_image)
+    landmarker.close()
+
+    if not result.face_landmarks:
+        return []
+
+    return result.face_landmarks
+
+
+def _detect_face_mesh(img_array, max_faces=10, min_confidence=0.5):
+    """Detect face mesh, trying legacy API first then falling back to tasks API."""
+    try:
+        return _mesh_with_solutions(img_array, max_faces, min_confidence)
+    except AttributeError:
+        return _mesh_with_tasks(img_array, max_faces, min_confidence)
+
+
 def main():
     input_path = sys.argv[1]
     output_path = sys.argv[2]
@@ -65,28 +138,19 @@ def main():
             format_label = "jpg"
 
         try:
-            import mediapipe as mp
             import numpy as np
             import cv2
 
             emit_progress(25, "Detecting faces")
 
             img_array = np.array(img)
-            mesh = mp.solutions.face_mesh.FaceMesh(
-                static_image_mode=True,
-                max_num_faces=10,
-                refine_landmarks=True,
-                min_detection_confidence=0.5,
-            )
-            results = mesh.process(img_array)
-            mesh.close()
 
-            faces_detected = 0
+            # Try legacy mp.solutions API first, fall back to mp.tasks
+            all_face_landmarks = _detect_face_mesh(img_array)
+
+            faces_detected = len(all_face_landmarks)
             eyes_corrected = 0
 
-            if results.multi_face_landmarks:
-                faces_detected = len(results.multi_face_landmarks)
-
             emit_progress(50, "Analyzing eyes")
 
             # Iris landmark indices
@@ -95,8 +159,7 @@ def main():
 
             if faces_detected > 0:
                 all_eyes = []
-                for face_landmarks in results.multi_face_landmarks:
-                    landmarks = face_landmarks.landmark
+                for landmarks in all_face_landmarks:
                     for iris_indices in [right_iris, left_iris]:
                         center_idx = iris_indices[0]
                         contour_indices = iris_indices[1:]

packages/ai/python/restore.py

@@ -217,6 +217,24 @@ def _get_codeformer_path():
     return CODEFORMER_LOCAL_PATH
 
 
+# ── Model path for new mp.tasks API ─────────────────────────────────
+
+_FACE_DETECT_MODEL_URL = "https://storage.googleapis.com/mediapipe-models/face_detector/blaze_face_short_range/float16/latest/blaze_face_short_range.task"
+_FACE_DETECT_MODEL_DIR = os.path.join(os.path.dirname(__file__), "..", "..", "..", ".models")
+_FACE_DETECT_MODEL_PATH = os.path.join(_FACE_DETECT_MODEL_DIR, "blaze_face_short_range.task")
+
+
+def _ensure_face_detect_model():
+    """Download the face detector model if not present."""
+    if os.path.exists(_FACE_DETECT_MODEL_PATH):
+        return _FACE_DETECT_MODEL_PATH
+    os.makedirs(_FACE_DETECT_MODEL_DIR, exist_ok=True)
+    import urllib.request
+    emit_progress(15, "Downloading face detection model")
+    urllib.request.urlretrieve(_FACE_DETECT_MODEL_URL, _FACE_DETECT_MODEL_PATH)
+    return _FACE_DETECT_MODEL_PATH
+
+
 def enhance_faces(img_bgr, fidelity=0.7):
     """Enhance faces in the image using CodeFormer ONNX.
 
@@ -239,20 +257,57 @@ def enhance_faces(img_bgr, fidelity=0.7):
     img_rgb = cv2.cvtColor(img_bgr, cv2.COLOR_BGR2RGB)
     ih, iw = img_bgr.shape[:2]
 
-    mp_face = mp.solutions.face_detection
-    detections = []
-    for model_sel in [0, 1]:
-        detector = mp_face.FaceDetection(
-            model_selection=model_sel, min_detection_confidence=0.4
-        )
-        results = detector.process(img_rgb)
-        detector.close()
-        if results.detections:
-            detections = results.detections
-            break
+    try:
+        mp_face = mp.solutions.face_detection
+        detections = []
+        for model_sel in [0, 1]:
+            detector = mp_face.FaceDetection(
+                model_selection=model_sel, min_detection_confidence=0.4
+            )
+            results = detector.process(img_rgb)
+            detector.close()
+            if results.detections:
+                detections = results.detections
+                break
 
-    if not detections:
-        return img_bgr, 0
+        if not detections:
+            return img_bgr, 0
+
+        face_boxes = []
+        for detection in detections:
+            bbox = detection.location_data.relative_bounding_box
+            face_boxes.append({
+                "x": int(bbox.xmin * iw),
+                "y": int(bbox.ymin * ih),
+                "w": int(bbox.width * iw),
+                "h": int(bbox.height * ih),
+            })
+
+    except AttributeError:
+        # mediapipe >= 0.10.30 removed mp.solutions, use tasks API
+        model_path = _ensure_face_detect_model()
+        options = mp.tasks.vision.FaceDetectorOptions(
+            base_options=mp.tasks.BaseOptions(model_asset_path=model_path),
+            running_mode=mp.tasks.vision.RunningMode.IMAGE,
+            min_detection_confidence=0.4,
+        )
+        fd = mp.tasks.vision.FaceDetector.create_from_options(options)
+        mp_image = mp.Image(image_format=mp.ImageFormat.SRGB, data=img_rgb)
+        result = fd.detect(mp_image)
+        fd.close()
+
+        if not result.detections:
+            return img_bgr, 0
+
+        face_boxes = []
+        for detection in result.detections:
+            bbox = detection.bounding_box
+            face_boxes.append({
+                "x": bbox.origin_x,
+                "y": bbox.origin_y,
+                "w": bbox.width,
+                "h": bbox.height,
+            })
 
     # Load CodeFormer model
     model_path = _get_codeformer_path()
@@ -266,13 +321,11 @@ def enhance_faces(img_bgr, fidelity=0.7):
     result = img_bgr.copy()
     faces_enhanced = 0
 
-    for detection in detections:
-        bbox = detection.location_data.relative_bounding_box
-        # Convert relative coords to absolute
-        x = int(bbox.xmin * iw)
-        y = int(bbox.ymin * ih)
-        w = int(bbox.width * iw)
-        h = int(bbox.height * ih)
+    for face_box in face_boxes:
+        x = face_box["x"]
+        y = face_box["y"]
+        w = face_box["w"]
+        h = face_box["h"]
 
         # Skip very small faces (under 48px) - enhancement won't help
         if w < 48 or h < 48: