leandroamaral/segany2 – API reference

leandroamaral / segany2

Public
2 runs

Run leandroamaral/segany2 with an API

Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.

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
model_name	string (enum)	FastSAM-x Options: FastSAM-x, FastSAM-s	choose a model
iou	number	0.7	iou threshold for filtering the annotations
text_prompt	string		use text prompt eg: "a black dog"
conf	number	0.25	object confidence threshold
retina	boolean	True	draw high-resolution segmentation masks
box_prompt	string	[0,0,0,0]	[x,y,w,h]
point_prompt	string	[[0,0]]	[[x1,y1],[x2,y2]]
point_label	string	[0]	[1,0] 0:background, 1:foreground
withContours	boolean	False	draw the edges of the masks
better_quality	boolean	False	better quality using morphologyEx

{
  "type": "object",
  "title": "Input",
  "required": [
    "image"
  ],
  "properties": {
    "iou": {
      "type": "number",
      "title": "Iou",
      "default": 0.7,
      "x-order": 2,
      "description": "iou threshold for filtering the annotations"
    },
    "conf": {
      "type": "number",
      "title": "Conf",
      "default": 0.25,
      "x-order": 4,
      "description": "object confidence threshold"
    },
    "image": {
      "type": "string",
      "title": "Image",
      "format": "uri",
      "x-order": 0,
      "description": "Input image"
    },
    "retina": {
      "type": "boolean",
      "title": "Retina",
      "default": true,
      "x-order": 5,
      "description": "draw high-resolution segmentation masks"
    },
    "box_prompt": {
      "type": "string",
      "title": "Box Prompt",
      "default": "[0,0,0,0]",
      "x-order": 6,
      "description": "[x,y,w,h]"
    },
    "model_name": {
      "enum": [
        "FastSAM-x",
        "FastSAM-s"
      ],
      "type": "string",
      "title": "model_name",
      "description": "choose a model",
      "default": "FastSAM-x",
      "x-order": 1
    },
    "point_label": {
      "type": "string",
      "title": "Point Label",
      "default": "[0]",
      "x-order": 8,
      "description": "[1,0] 0:background, 1:foreground"
    },
    "text_prompt": {
      "type": "string",
      "title": "Text Prompt",
      "x-order": 3,
      "description": "use text prompt eg: \"a black dog\""
    },
    "point_prompt": {
      "type": "string",
      "title": "Point Prompt",
      "default": "[[0,0]]",
      "x-order": 7,
      "description": "[[x1,y1],[x2,y2]]"
    },
    "withContours": {
      "type": "boolean",
      "title": "Withcontours",
      "default": false,
      "x-order": 9,
      "description": "draw the edges of the masks"
    },
    "better_quality": {
      "type": "boolean",
      "title": "Better Quality",
      "default": false,
      "x-order": 10,
      "description": "better quality using morphologyEx"
    }
  }
}

Output schema

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

Schema

{
  "type": "string",
  "title": "Output",
  "format": "uri"
}