GroundedSAM

GroundedSAM takes an input image and prompt to generate a language-guided mask.

Try it in the Widget Center

Click this url to try this widget and copy the Pro Config template.

Usage

<TODO: enter description here, and remove useless inputs>

Input Parameters

Name	Type	Description	Default	Required
image	string	HTTP url. Input image for Grounded SAM. We will create a mask for the image based on your text prompt.
mask_prompt	string	The text prompt for masking
negative_mask_prompt	string	The negative text prompt for masking (exclude something here)
adjustment_factor	integer	Mask Adjustment Factor	0

Output Parameters

Name	Type	Description	File Type
url_image	string	Annotated image with mask bbox and text. The image that was generated has been saved as an online URL. This link is temporary, so please save it for your own use	image
url_mask	string	The binary mask. The video that was generated has been saved as an online URL. This link is temporary, so please save it for your own use	image

Output Example

success

{ // input image = https://image.myshell.ai/image/chat/embed_obj/40295/20240423/1bfc157b73284d028e9217ce380c8363.png, mask_prompt = person, negative_mask_prompt = pants, adjustment_factor = 0
  "url_image": "https://image.myshell.ai/image/chat/embed_obj/40295/20240423/25431166f5d74e058832b0811c04806c.jpg",
  "url_mask": "https://image.myshell.ai/image/chat/embed_obj/40295/20240423/4dfc2764d4914460a2ffd8506b328b7d.jpg"
}

fail

{
   "results": "<the example results of this widget>"
}