zedge/sam3-image | API reference

Public

21.9K runs

Run zedge/sam3-image 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 file
prompt	string	person	Text prompt for segmentation
threshold	number	0.5 Max: 1	Confidence threshold for object detection
save_overlay	boolean	False	If True, includes the overlay image in the ZIP file
mask_only	boolean	False	If True, returns a black-and-white mask image instead of an overlay on the original image
return_zip	boolean	True	If True, returns a ZIP file containing individual masks as PNGs
mask_opacity	number	0.5 Max: 1	Opacity of the mask overlay (0.0 to 1.0)
mask_color	string	green	Color of the mask overlay. Options: 'green', 'red', 'blue', 'yellow', 'cyan', 'magenta'
warm_delay	integer		Parameter for warming the model. If set, returns nothing after the specified number of seconds

{
  "type": "object",
  "title": "Input",
  "properties": {
    "image": {
      "type": "string",
      "title": "Image",
      "format": "uri",
      "x-order": 0,
      "description": "Input image file"
    },
    "prompt": {
      "type": "string",
      "title": "Prompt",
      "default": "person",
      "x-order": 1,
      "description": "Text prompt for segmentation"
    },
    "mask_only": {
      "type": "boolean",
      "title": "Mask Only",
      "default": false,
      "x-order": 4,
      "description": "If True, returns a black-and-white mask image instead of an overlay on the original image"
    },
    "threshold": {
      "type": "number",
      "title": "Threshold",
      "default": 0.5,
      "maximum": 1,
      "minimum": 0,
      "x-order": 2,
      "description": "Confidence threshold for object detection"
    },
    "mask_color": {
      "type": "string",
      "title": "Mask Color",
      "default": "green",
      "x-order": 7,
      "description": "Color of the mask overlay. Options: 'green', 'red', 'blue', 'yellow', 'cyan', 'magenta'"
    },
    "return_zip": {
      "type": "boolean",
      "title": "Return Zip",
      "default": true,
      "x-order": 5,
      "description": "If True, returns a ZIP file containing individual masks as PNGs"
    },
    "warm_delay": {
      "type": "integer",
      "title": "Warm Delay",
      "x-order": 8,
      "description": "Parameter for warming the model. If set, returns nothing after the specified number of seconds"
    },
    "mask_opacity": {
      "type": "number",
      "title": "Mask Opacity",
      "default": 0.5,
      "maximum": 1,
      "minimum": 0,
      "x-order": 6,
      "description": "Opacity of the mask overlay (0.0 to 1.0)"
    },
    "save_overlay": {
      "type": "boolean",
      "title": "Save Overlay",
      "default": false,
      "x-order": 3,
      "description": "If True, includes the overlay image in the ZIP file"
    }
  }
}

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"
}