devarsh-mavani-19/sam3 | API reference

Public

3 runs

Run devarsh-mavani-19/sam3 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 to segment.
text_prompt	string	object	Text description of the object(s) to segment (e.g. "yellow school bus", "person wearing red").
box_prompt	string		Optional: bounding box as JSON [x1, y1, x2, y2] in pixel coordinates. Example: "[100, 200, 400, 500]".
confidence_threshold	number	0.5 Max: 1	Minimum confidence score to include a mask in output.
mask_opacity	number	0.5 Max: 1	Opacity of the mask overlay on the visualization.
mask_color	None	green	Color of the mask overlay.
output_format	None	png	'png' returns annotated image; 'json' returns masks, boxes, and scores.

{
  "type": "object",
  "title": "Input",
  "required": [
    "image"
  ],
  "properties": {
    "image": {
      "type": "string",
      "title": "Image",
      "format": "uri",
      "x-order": 0,
      "description": "Input image to segment."
    },
    "box_prompt": {
      "type": "string",
      "title": "Box Prompt",
      "x-order": 2,
      "nullable": true,
      "description": "Optional: bounding box as JSON [x1, y1, x2, y2] in pixel coordinates. Example: \"[100, 200, 400, 500]\"."
    },
    "mask_color": {
      "enum": [
        "green",
        "red",
        "blue",
        "yellow",
        "cyan",
        "magenta"
      ],
      "type": "string",
      "title": "mask_color",
      "description": "Color of the mask overlay.",
      "default": "green",
      "x-order": 5
    },
    "text_prompt": {
      "type": "string",
      "title": "Text Prompt",
      "default": "object",
      "x-order": 1,
      "description": "Text description of the object(s) to segment (e.g. \"yellow school bus\", \"person wearing red\")."
    },
    "mask_opacity": {
      "type": "number",
      "title": "Mask Opacity",
      "default": 0.5,
      "maximum": 1,
      "minimum": 0,
      "x-order": 4,
      "description": "Opacity of the mask overlay on the visualization."
    },
    "output_format": {
      "enum": [
        "png",
        "json"
      ],
      "type": "string",
      "title": "output_format",
      "description": "'png' returns annotated image; 'json' returns masks, boxes, and scores.",
      "default": "png",
      "x-order": 6
    },
    "confidence_threshold": {
      "type": "number",
      "title": "Confidence Threshold",
      "default": 0.5,
      "maximum": 1,
      "minimum": 0,
      "x-order": 3,
      "description": "Minimum confidence score to include a mask in output."
    }
  }
}

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"
}