segment-anything-model

Name: segment-anything-model
Availability: InStock
Author: eddielueng

Generate object masks from point, box, or mask prompts via SAM.

1|Updated Apr 14, 2026

Search Tags:#prompt engineering #computer vision #zero-shot #image segmentation #mask generation #segment-anything #ONNX deployment

Ready to run

npx skills add https://github.com/eddielueng/hermes-agent-zh --skill segment-anything-model-eddielueng

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: segment-anything-model
Source: https://github.com/eddielueng/hermes-agent-zh/tree/main/skills/mlops/models/segment-anything
Command: npx skills add https://github.com/eddielueng/hermes-agent-zh --skill segment-anything-model-eddielueng

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill solves the problem of extracting accurate object masks from images without training task-specific segmentation models.

Core Features & Use Cases

Zero-shot image segmentation: Produce object masks in new domains without fine-tuning.
Prompt flexibility: Use point prompts, bounding boxes, or even previous masks for refinement.
Automatic mask generation: Generate candidate masks for all objects, then filter by quality metrics.
Deployment-ready: Includes guidance for ONNX export for faster inference and broader integration.

Use SAM when you need to quickly segment any object in images for annotation assistance, training data generation, or extracting regions of interest (e.g., people, vehicles, parts) using interactive or automatic workflows.

Quick Start

Download the SAM checkpoint for the model size you want, then load it and run segmentation with a point or box prompt to get masks for the target object.

Frequently Asked Questions about segment-anything-model

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I generate object masks from an image without training a new model?▼

Zero-shot image segmentation generates accurate object masks from new domains without fine-tuning. You can produce masks by providing prompt inputs like points or bounding boxes to guide the segmentation of your target objects.

What is zero-shot image segmentation and when do I need it?▼

Zero-shot image segmentation extracts accurate object masks from images without requiring task-specific training data. You need it to quickly segment any object for annotation assistance, training data generation, or extracting regions of interest.

Can I use point prompts and bounding boxes for interactive image segmentation?▼

Yes, prompt flexibility allows you to use point prompts, bounding boxes, or even previous masks for interactive image segmentation. This enables prompt refinement loops to accurately extract and adjust object boundaries.

How do I export and deploy image segmentation models for faster inference?▼

You can achieve deployment-ready faster inference by exporting image segmentation models via ONNX. This allows broader integration into image segmentation pipelines and accelerates mask generation across different platforms.

How do I automatically generate and filter candidate masks for all objects in an image?▼

Automatic mask generation produces candidate masks for all objects in an image simultaneously. You can then filter these generated masks by their usable scoring and quality outputs to retain the most accurate segmentations.