fix: More robust handling of feathered_mask normalization

This commit provides a more robust fix for the RuntimeWarning
(invalid value encountered in divide/cast) that could occur in
the `apply_mouth_area` function within
`modules/processors/frame/face_swapper.py`.

The previous check for `feathered_mask.max() == 0` was not
sufficient for all floating point edge cases.

The updated logic now:
- Checks if `feathered_mask.max()` is less than a small epsilon (1e-6).
- If true, it logs a warning and explicitly sets `feathered_mask`
  to an all-zero `uint8` array of the correct shape.
- Otherwise, it proceeds with the normalization and casting to `uint8`.

This ensures that division by zero or by extremely small numbers is
prevented, and the `feathered_mask` is always in a valid state for
subsequent blending operations.

modules/processors/frame/face_swapper.py

@@ -553,11 +553,13 @@ def apply_mouth_area(
         feathered_mask = cv2.GaussianBlur(
             polygon_mask.astype(float), (0, 0), feather_amount
         )
-        if feathered_mask.max() == 0:
-            logging.warning("Mouth mask's feathered_mask is all zeros. Skipping normalization to prevent division by zero.")
-            # feathered_mask remains all zeros, which is safe for subsequent blending
+
+        mask_max_value = feathered_mask.max()
+        if mask_max_value < 1e-6:  # Check if max is effectively zero
+            logging.warning("Mouth mask's feathered_mask is all zeros or near-zeros after blur. Resulting mask will be black.")
+            feathered_mask = np.zeros_like(polygon_mask, dtype=np.uint8)
         else:
-            feathered_mask = (feathered_mask / feathered_mask.max() * 255).astype(np.uint8)
+            feathered_mask = (feathered_mask / mask_max_value * 255).astype(np.uint8)
 
         face_mask_roi = face_mask[min_y:max_y, min_x:max_x]
         combined_mask = feathered_mask * (face_mask_roi / 255.0)