BodyGenSegmentAnything2

Fields

Field	Type	Required	Description
`image`	components.BodyGenSegmentAnything2Image	✔️	Image to segment.
`model_id`	Optional[str]	➖	Hugging Face model ID used for image generation.
`point_coords`	Optional[str]	➖	Nx2 array of point prompts to the model, where each point is in (X,Y) in pixels.
`point_labels`	Optional[str]	➖	Labels for the point prompts, where 1 indicates a foreground point and 0 indicates a background point.
`box`	Optional[str]	➖	A length 4 array given as a box prompt to the model, in XYXY format.
`mask_input`	Optional[str]	➖	A low-resolution mask input to the model, typically from a previous prediction iteration, with the form 1xHxW (H=W=256 for SAM).
`multimask_output`	Optional[bool]	➖	If true, the model will return three masks for ambiguous input prompts, often producing better masks than a single prediction.
`return_logits`	Optional[bool]	➖	If true, returns un-thresholded mask logits instead of a binary mask.
`normalize_coords`	Optional[bool]	➖	If true, the point coordinates will be normalized to the range [0,1], with point_coords expected to be with respect to image dimensions.