You're looking at a specific version of this model. Jump to the model overview.
yodagg /sam3-image-seg:29c8e52d
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
|
|
| prompt |
string
|
Text prompt describing what to segment
|
|
| multimask_output |
boolean
|
True
|
Return multiple masks for ambiguous prompts
|
| confidence_threshold |
number
|
0.5
Max: 1 |
Minimum score to keep a mask
|
| max_masks |
integer
|
20
Min: 1 Max: 100 |
Maximum number of masks to return
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'properties': {'orig_img_h': {'title': 'Orig Img H', 'type': 'integer'},
'orig_img_w': {'title': 'Orig Img W', 'type': 'integer'},
'pred_boxes': {'items': {'items': {'type': 'number'},
'type': 'array'},
'title': 'Pred Boxes',
'type': 'array'},
'pred_masks': {'items': {},
'title': 'Pred Masks',
'type': 'array'},
'pred_scores': {'items': {'type': 'number'},
'title': 'Pred Scores',
'type': 'array'},
'visualization': {'format': 'uri',
'title': 'Visualization',
'type': 'string'}},
'required': ['visualization',
'pred_masks',
'pred_boxes',
'pred_scores',
'orig_img_h',
'orig_img_w'],
'title': 'Output',
'type': 'object'}