You're looking at a specific version of this model. Jump to the model overview.
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 |
|---|---|---|---|
| image |
string
|
Input image, accepts JPG, JPEG, PNG, WEBP files.
|
|
| prompts |
array
|
List of per concept JSON strings that represent prompt objects, that contain: text (string), positive_boxes (list of lists of four floats), negative_boxes (list of lists of four floats), positive_points (list of lists of two floats), negative_points (list of lists of two floats). At least one of text, positive_boxes or positive_points must be provided.All coordinates are normalized to the range [0, 1]. Boxes are in the format of: center_x, center_y, width, height.
|
|
| confidence_threshold |
number
|
0.5
Min: 0.01 Max: 0.99 |
Confidence threshold for the model
|
| visualize |
boolean
|
False
|
Whether to return prediction results as per prompt PNG file.
|
| backbone_output |
boolean
|
False
|
Whether to return the backbone output as a PT file.
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'description': 'Class defining structure of the output.\n'
'\n'
'Attributes:\n'
' results (list[Path]): List of paths to the JSON files '
'containing the prediction results.\n'
' visualizations (list[Path]): List of paths to the PNG '
'files containing the visualizations.\n'
' backbone_outputs (Path): Path to the file containing the '
'backbone outputs.',
'properties': {'backbone_outputs': {'format': 'uri',
'nullable': True,
'title': 'Backbone Outputs',
'type': 'string'},
'results': {'items': {'anyOf': [],
'format': 'uri',
'type': 'string'},
'nullable': True,
'title': 'Results',
'type': 'array'},
'visualizations': {'items': {'anyOf': [],
'format': 'uri',
'type': 'string'},
'nullable': True,
'title': 'Visualizations',
'type': 'array'}},
'required': [],
'title': 'Sam3Output',
'type': 'object'}