You're looking at a specific version of this model. Jump to the model overview.
lucataco /segment-anything-2:be7cbde9
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
|
|
| mask_limit |
integer
|
-1
|
maximum number of masks to return. If -1 or None, all masks will be returned. NOTE: The masks are sorted by predicted_iou.
|
| points_per_side |
integer
|
64
|
The number of points to be sampled along one side of the image.
|
| points_per_batch |
integer
|
128
|
Sets the number of points run simultaneously by the model
|
| pred_iou_thresh |
number
|
0.7
|
A filtering threshold in [0,1], using the model's predicted mask quality.
|
| stability_score_thresh |
number
|
0.92
|
A filtering threshold in [0,1], using the stability of the mask under changes to the cutoff used to binarize the model's mask predictions.
|
| stability_score_offset |
number
|
0.7
|
The amount to shift the cutoff when calculated the stability score.
|
| crop_n_layers |
integer
|
1
|
If >0, mask prediction will be run again on crops of the image
|
| box_nms_thresh |
number
|
0.7
|
The box IoU cutoff used by non-maximal suppression to filter duplicate masks.
|
| crop_n_points_downscale_factor |
integer
|
2
|
The number of points-per-side sampled in layer n is scaled down by crop_n_points_downscale_factor**n.
|
| min_mask_region_area |
number
|
25
|
If >0, postprocessing will be applied to remove disconnected regions and holes in masks with area smaller than min_mask_region_area.
|
| mask_2_mask |
boolean
|
True
|
Whether to add a one step refinement using previous mask predictions.
|
| multimask_output |
boolean
|
False
|
Whether to output multimask at each point of the grid.
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'items': {'format': 'uri', 'type': 'string'},
'title': 'Output',
'type': 'array'}