sorry for not responding earlier. I had some health issues and needed to rest. Well, I wanted to let you know that my issue has been resolved. Let me explain how I managed to do this: I used a function that was already created by the developers to mark these images. You can find this function on the official Mediapipe page. From what I see, the function accesses the result directly and processes it to mark it on the image. Thank you so much to everyone who supported me!

https://ai.google.dev/edge/mediapipe/solutions/vision/face_detector/python?hl=pt-br