🤖 Model

fire/v-sekai.mediapipe-labeler
Label facial blendshapes and body pose in images or videos. Detect up to 100 people and output JSON annotations with Med...
Found 3 models (showing 1-3)
Label facial blendshapes and body pose in images or videos. Detect up to 100 people and output JSON annotations with Med...
Estimate human body poses in an input image and return an annotated image with keypoints and skeletal connections. Detec...
Estimate human pose or depth from an input image, returning an OpenPose skeleton/keypoint map or a depth map image. Opti...