You're looking at a specific version of this model. Jump to the model overview.

fire /v-sekai.mediapipe-labeler:2dc3055a

Playground API

Input schema

The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.

Field Type Default value Description
media_path
string
Input image or video file
max_people
integer
100

Min: 1

Max: 100

Maximum number of people to detect (1-100)
frame_sample_rate
integer
1

Min: 1

Process every nth frame for video input

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema 
{'properties': {'blendshapes': {'format': 'uri',
                                'title': 'Blendshapes',
                                'type': 'string'},
                'debug_media': {'format': 'uri',
                                'title': 'Debug Media',
                                'type': 'string'},
                'fullbody_data': {'format': 'uri',
                                  'title': 'Fullbody Data',
                                  'type': 'string'},
                'hand_landmarks': {'format': 'uri',
                                   'title': 'Hand Landmarks',
                                   'type': 'string'},
                'media_type': {'title': 'Media Type', 'type': 'string'},
                'mediapipe_keypoints': {'format': 'uri',
                                        'title': 'Mediapipe Keypoints',
                                        'type': 'string'},
                'num_people': {'title': 'Num People', 'type': 'integer'},
                'total_frames': {'title': 'Total Frames', 'type': 'integer'}},
 'required': ['mediapipe_keypoints',
              'blendshapes',
              'fullbody_data',
              'debug_media',
              'num_people',
              'media_type'],
 'title': 'Output',
 'type': 'object'}