deal with mask

app.py

@@ -53,32 +53,36 @@ def create_face_mask(pil_image):
     Create a binary mask (PIL Image) from a PIL image by detecting the face region.
     The mask will be white (255) on the detected face area and black (0) elsewhere.
     """
-    # Convert PIL image to a numpy array in RGB format
-    image_np = np.array(pil_image.convert("RGB"))
-    # Convert to grayscale for face detection
-    gray = cv2.cvtColor(image_np, cv2.COLOR_RGB2GRAY)
-
-    # Load the Haar cascade for face detection (make sure opencv data is installed)
-    cascade_path = cv2.data.haarcascades + "haarcascade_frontalface_default.xml"
-    face_cascade = cv2.CascadeClassifier(cascade_path)
-
-    # Detect faces in the image
-    faces = face_cascade.detectMultiScale(gray, scaleFactor=1.1, minNeighbors=5)
-
-    # Create an empty mask with the same dimensions as the image
-    mask = np.zeros_like(gray, dtype=np.uint8)
-
-    # For each detected face, draw a white rectangle (or a more refined shape)
-    for (x, y, w, h) in faces:
-        # Optionally expand the bounding box slightly
-        padding = 0.2
-        x1 = max(0, int(x - w * padding))
-        y1 = max(0, int(y - h * padding))
-        x2 = min(gray.shape[1], int(x + w * (1 + padding)))
-        y2 = min(gray.shape[0], int(y + h * (1 + padding)))
-        mask[y1:y2, x1:x2] = 255
-
-    return Image.fromarray(mask)
+    try:
+        # Convert PIL image to a numpy array in RGB format
+        image_np = np.array(pil_image.convert("RGB"))
+        # Convert to grayscale for face detection
+        gray = cv2.cvtColor(image_np, cv2.COLOR_RGB2GRAY)
+
+        # Load the Haar cascade for face detection (make sure opencv data is installed)
+        cascade_path = cv2.data.haarcascades + "haarcascade_frontalface_default.xml"
+        face_cascade = cv2.CascadeClassifier(cascade_path)
+
+        # Detect faces in the image
+        faces = face_cascade.detectMultiScale(gray, scaleFactor=1.1, minNeighbors=5)
+
+        # Create an empty mask with the same dimensions as the image
+        mask = np.zeros_like(gray, dtype=np.uint8)
+
+        # For each detected face, draw a white rectangle (or a more refined shape)
+        for (x, y, w, h) in faces:
+            # Optionally expand the bounding box slightly
+            padding = 0.2
+            x1 = max(0, int(x - w * padding))
+            y1 = max(0, int(y - h * padding))
+            x2 = min(gray.shape[1], int(x + w * (1 + padding)))
+            y2 = min(gray.shape[0], int(y + h * (1 + padding)))
+            mask[y1:y2, x1:x2] = 255
+
+        return Image.fromarray(mask)
+    except Exception as e:
+        print(f"Error: {e}")
+        raise ValueError('A very specific bad thing happened.')
 
 def face_swap_app(target_img, face_img):
     if target_img is None or face_img is None:

modules/ace_plus_ldm.py

@@ -100,6 +100,10 @@ class LatentDiffusionACEPlus(LatentDiffusion):
     @torch.no_grad()
     def encode_first_stage(self, x, **kwargs):
         def run_one_image(u):
+            if u is None:
+                print(f"Warning: input is None!")
+            else:
+                print(f"Input shape: {u.shape}")
             zu = self.first_stage_model.encode(u)
             if isinstance(zu, (tuple, list)):
                 zu = zu[0]