diff --git a/mediapipe/tasks/ios/vision/face_detector/sources/MPPFaceDetector.h b/mediapipe/tasks/ios/vision/face_detector/sources/MPPFaceDetector.h
index 885a490715..21c1b11503 100644
--- a/mediapipe/tasks/ios/vision/face_detector/sources/MPPFaceDetector.h
+++ b/mediapipe/tasks/ios/vision/face_detector/sources/MPPFaceDetector.h
@@ -84,11 +84,9 @@ NS_SWIFT_NAME(FaceDetector)
  * interest. Rotation will be applied according to the `orientation` property of the provided
  * `MPImage`. Only use this method when the `FaceDetector` is created with running mode `.image`.
  *
- * This method supports classification of RGBA images. If your `MPImage` has a source type of
- * `.pixelBuffer` or `.sampleBuffer`, the underlying pixel buffer must have one of the
- * following pixel format types:
- * 1. kCVPixelFormatType_32BGRA
- * 2. kCVPixelFormatType_32RGBA
+ * This method supports performing face detection on RGBA images. If your `MPImage` has a source
+ * type of `.pixelBuffer` or `.sampleBuffer`, the underlying pixel buffer must use
+ * `kCVPixelFormatType_32BGRA` as its pixel format.
  *
  * If your `MPImage` has a source type of `.image` ensure that the color space is
  * RGB with an Alpha channel.
@@ -109,11 +107,9 @@ NS_SWIFT_NAME(FaceDetector)
  * the provided `MPImage`. Only use this method when the `FaceDetector` is created with running
  * mode `.video`.
  *
- * This method supports classification of RGBA images. If your `MPImage` has a source type of
- * `.pixelBuffer` or `.sampleBuffer`, the underlying pixel buffer must have one of the
- * following pixel format types:
- * 1. kCVPixelFormatType_32BGRA
- * 2. kCVPixelFormatType_32RGBA
+ * This method supports performing face detection on RGBA images. If your `MPImage` has a source
+ * type of `.pixelBuffer` or `.sampleBuffer`, the underlying pixel buffer must use
+ * `kCVPixelFormatType_32BGRA` as its pixel format.
  *
  * If your `MPImage` has a source type of `.image` ensure that the color space is RGB with an Alpha
  * channel.
@@ -145,17 +141,15 @@ NS_SWIFT_NAME(FaceDetector)
  * It's required to provide a timestamp (in milliseconds) to indicate when the input image is sent
  * to the face detector. The input timestamps must be monotonically increasing.
  *
- * This method supports classification of RGBA images. If your `MPImage` has a source type of
- * `.pixelBuffer` or `.sampleBuffer`, the underlying pixel buffer must have one of the
- * following pixel format types:
- * 1. kCVPixelFormatType_32BGRA
- * 2. kCVPixelFormatType_32RGBA
+ * This method supports performing face detection on RGBA images. If your `MPImage` has a source
+ * type of `.pixelBuffer` or `.sampleBuffer`, the underlying pixel buffer must use
+ * `kCVPixelFormatType_32BGRA` as its pixel format.
  *
  * If the input `MPImage` has a source type of `.image` ensure that the color
  * space is RGB with an Alpha channel.
  *
  * If this method is used for classifying live camera frames using `AVFoundation`, ensure that you
- * request `AVCaptureVideoDataOutput` to output frames in `kCMPixelFormat_32RGBA` using its
+ * request `AVCaptureVideoDataOutput` to output frames in `kCMPixelFormat_32BGRA` using its
  * `videoSettings` property.
  *
  * @param image A live stream image data of type `MPImage` on which face detection is to be
diff --git a/mediapipe/tasks/ios/vision/face_landmarker/sources/MPPFaceLandmarker.h b/mediapipe/tasks/ios/vision/face_landmarker/sources/MPPFaceLandmarker.h
index 53cb8ecd71..13ecd7387d 100644
--- a/mediapipe/tasks/ios/vision/face_landmarker/sources/MPPFaceLandmarker.h
+++ b/mediapipe/tasks/ios/vision/face_landmarker/sources/MPPFaceLandmarker.h
@@ -57,11 +57,9 @@ NS_SWIFT_NAME(FaceLandmarker)
  * interest. Rotation will be applied according to the `orientation` property of the provided
  * `MPImage`. Only use this method when the `FaceLandmarker` is created with `.image`.
  *
- * This method supports RGBA images. If your `MPImage` has a source type of `.pixelBuffer` or
- * `.sampleBuffer`, the underlying pixel buffer must have one of the following pixel format
- * types:
- * 1. kCVPixelFormatType_32BGRA
- * 2. kCVPixelFormatType_32RGBA
+ * This method supports performing face landmark detection on RGBA images. If your `MPImage` has a
+ * source type of `.pixelBuffer` or `.sampleBuffer`, the underlying pixel buffer must use
+ * `kCVPixelFormatType_32BGRA` as its pixel format.
  *
  * If your `MPImage` has a source type of `.image` ensure that the color space is RGB with an
  * Alpha channel.
@@ -80,10 +78,9 @@ NS_SWIFT_NAME(FaceLandmarker)
  * the provided `MPImage`. Only use this method when the `FaceLandmarker` is created with running
  * mode `.video`.
  *
- * This method supports RGBA images. If your `MPImage` has a source type of `.pixelBuffer` or
- * `.sampleBuffer`, the underlying pixel buffer must have one of the following pixel format types:
- * 1. kCVPixelFormatType_32BGRA
- * 2. kCVPixelFormatType_32RGBA
+ * This method supports performing face landmark detection on RGBA images. If your `MPImage` has a
+ * source type of `.pixelBuffer` or `.sampleBuffer`, the underlying pixel buffer must use
+ * `kCVPixelFormatType_32BGRA` as its pixel format.
  *
  * If your `MPImage` has a source type of `.image` ensure that the color space is RGB with an Alpha
  * channel.
@@ -113,16 +110,15 @@ NS_SWIFT_NAME(FaceLandmarker)
  * It's required to provide a timestamp (in milliseconds) to indicate when the input image is sent
  * to the face detector. The input timestamps must be monotonically increasing.
  *
- * This method supports RGBA images. If your `MPImage` has a source type of `.pixelBuffer` or
- * `.sampleBuffer`, the underlying pixel buffer must have one of the following pixel format types:
- * 1. kCVPixelFormatType_32BGRA
- * 2. kCVPixelFormatType_32RGBA
+ * This method supports performing face landmark detection on RGBA images. If your `MPImage` has a
+ * source type of `.pixelBuffer` or `.sampleBuffer`, the underlying pixel buffer must use
+ * `kCVPixelFormatType_32BGRA` as its pixel format.
  *
  * If the input `MPImage` has a source type of `.image` ensure that the color space is RGB with an
  * Alpha channel.
  *
  * If this method is used for classifying live camera frames using `AVFoundation`, ensure that you
- * request `AVCaptureVideoDataOutput` to output frames in `kCMPixelFormat_32RGBA` using its
+ * request `AVCaptureVideoDataOutput` to output frames in `kCMPixelFormat_32BGRA` using its
  * `videoSettings` property.
  *
  * @param image A live stream image data of type `MPImage` on which face landmark detection is to be
diff --git a/mediapipe/tasks/ios/vision/gesture_recognizer/sources/MPPGestureRecognizer.h b/mediapipe/tasks/ios/vision/gesture_recognizer/sources/MPPGestureRecognizer.h
index 4585087189..2b8e50c072 100644
--- a/mediapipe/tasks/ios/vision/gesture_recognizer/sources/MPPGestureRecognizer.h
+++ b/mediapipe/tasks/ios/vision/gesture_recognizer/sources/MPPGestureRecognizer.h
@@ -63,11 +63,9 @@ NS_SWIFT_NAME(GestureRecognizer)
  * `MPImage`. Only use this method when the `GestureRecognizer` is created with running mode,
  * `.image`.
  *
- * This method supports gesture recognition of RGBA images. If your `MPImage` has a source type of
- * `.pixelBuffer` or `.sampleBuffer`, the underlying pixel buffer must have one of the following
- * pixel format types:
- * 1. kCVPixelFormatType_32BGRA
- * 2. kCVPixelFormatType_32RGBA
+ * This method supports performing gesture recognition on RGBA images. If your `MPImage` has a
+ * source type of `.pixelBuffer` or `.sampleBuffer`, the underlying pixel buffer must use
+ * `kCVPixelFormatType_32BGRA` as its pixel format.
  *
  * If your `MPImage` has a source type of `.image` ensure that the color space is RGB with an Alpha
  * channel.
@@ -92,11 +90,9 @@ NS_SWIFT_NAME(GestureRecognizer)
  * It's required to provide the video frame's timestamp (in milliseconds). The input timestamps must
  * be monotonically increasing.
  *
- * This method supports gesture recognition of RGBA images. If your `MPImage` has a source type of
- * `.pixelBuffer` or `.sampleBuffer`, the underlying pixel buffer must have one of the following
- * pixel format types:
- * 1. kCVPixelFormatType_32BGRA
- * 2. kCVPixelFormatType_32RGBA
+ * This method supports performing gesture recognition on RGBA images. If your `MPImage` has a
+ * source type of `.pixelBuffer` or `.sampleBuffer`, the underlying pixel buffer must use
+ * `kCVPixelFormatType_32BGRA` as its pixel format.
  *
  * If your `MPImage` has a source type of `.image` ensure that the color space is RGB with an Alpha
  * channel.
@@ -129,18 +125,16 @@ NS_SWIFT_NAME(GestureRecognizer)
  * It's required to provide a timestamp (in milliseconds) to indicate when the input image is sent
  * to the gesture recognizer. The input timestamps must be monotonically increasing.
  *
- * This method supports gesture recognition of RGBA images. If your `MPImage` has a source type of
- * `.pixelBuffer` or `.sampleBuffer`, the underlying pixel buffer must have one of the following
- * pixel format types:
- * 1. kCVPixelFormatType_32BGRA
- * 2. kCVPixelFormatType_32RGBA
+ * This method supports performing gesture recognition on RGBA images. If your `MPImage` has a
+ * source type of `.pixelBuffer` or `.sampleBuffer`, the underlying pixel buffer must use
+ * `kCVPixelFormatType_32BGRA` as its pixel format.
  *
  * If the input `MPImage` has a source type of `.image` ensure that the color space is RGB with an
  * Alpha channel.
  *
  * If this method is used for performing gesture recognition on live camera frames using
  * `AVFoundation`, ensure that you request `AVCaptureVideoDataOutput` to output frames in
- * `kCMPixelFormat_32RGBA` using its `videoSettings` property.
+ * `kCMPixelFormat_32BGRA` using its `videoSettings` property.
  *
  * @param image A live stream image data of type `MPImage` on which gesture recognition is to be
  * performed.
diff --git a/mediapipe/tasks/ios/vision/image_classifier/sources/MPPImageClassifier.h b/mediapipe/tasks/ios/vision/image_classifier/sources/MPPImageClassifier.h
index 6e7ae57bfa..6b093b8c4d 100644
--- a/mediapipe/tasks/ios/vision/image_classifier/sources/MPPImageClassifier.h
+++ b/mediapipe/tasks/ios/vision/image_classifier/sources/MPPImageClassifier.h
@@ -199,7 +199,7 @@ NS_SWIFT_NAME(ImageClassifier)
  * Alpha channel.
  *
  * If this method is used for classifying live camera frames using `AVFoundation`, ensure that you
- * request `AVCaptureVideoDataOutput` to output frames in `kCMPixelFormat_32RGBA` using its
+ * request `AVCaptureVideoDataOutput` to output frames in `kCMPixelFormat_32BGRA` using its
  * `videoSettings` property.
  *
  * @param image A live stream image data of type `MPImage` on which image classification is to be