cyberneticlibrary

Segment objects in images with zero-shot transfer

segment-anything-modelskillsetup L29,423
Orchestra-Research/AI-Research-SKILLs
What it does

Foundation model for image segmentation with zero-shot transfer.

Best for

Use when you need to segment any object in images using points, boxes, or masks as prompts, or automatically generate all object masks in an image.

Inputs

Task context, parameters

Outputs

Executed skill results

Requires

Multimodal, Image Segmentation, Computer Vision

Preconditions

Dependencies: segment-anything, transformers>=4.30.0

Failure modes

Invalid context; Incomplete parameters

Trust signals

From Orchestra-Research/AI-Research-SKILLs; v1.0.0; MIT license