mediapipe
mediapipe copied to clipboard
How can I use the cartoon face?
Have I written custom code (as opposed to using a stock example script provided in MediaPipe)
Yes
OS Platform and Distribution
linux
MediaPipe Tasks SDK version
0.10.11
Task name (e.g. Image classification, Gesture recognition etc.)
Face Landmark Detection
Programming Language and version (e.g. C++, Python, Java)
Python
Describe the actual behavior
I don't know how to turn a face into a cartoon
Describe the expected behaviour
show the Cartoon face
Standalone code/steps you may have used to try to get what you need
I have successfully implemented Face Landmark Detection, which enables me to obtain all the points of the face. I can see that the face can be transformed into a cartoon bear face in the demo. May I ask how it is achieved? I did not find a code example, can you guide the implementation process, thank you
Other info / Complete Logs
cv2.VideoCapture(0)
use vision.FaceLandmarker model_asset_path='face_landmarker.task'
for i in range(len(face_landmarks)):
pos_x = int(face_landmarks[i].x * width)
pos_y = int(face_landmarks[i].y * height)
i success to get the points
Hi @327635328,
At present, we do not have any available Python examples for using the Avatar face. Please grant us some time to discuss this matter with the team. We will inform you whether we can provide the something on this or not.
Thank you!!
This issue has been marked stale because it has no recent activity since 7 days. It will be closed if no further activity occurs. Thank you.
This issue was closed due to lack of activity after being marked stale for past 7 days.
Hi @327635328,
Apologies for the delayed response. Based on our internal discussion, the avatar model is currently available only in the web version, which you can find here https://mediapipe-studio.webapps.google.com/studio/demo/face_landmarker. This version is not open source, so customization is not possible. Additionally, we have no current plans to provide an avatar demo in Python.
However, we encourage you to raise a feature request with detailed information on how this feature would benefit the community and its potential use cases. This feedback will help us consider its implementation in the future.
Thank you.
This issue has been marked stale because it has no recent activity since 7 days. It will be closed if no further activity occurs. Thank you.
This issue was closed due to lack of activity after being marked stale for past 7 days.