Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Segment images without training using SAM v1.0.0

Use this resource to segment objects in images, without training, using SAM

New

  • 593 downloads
  • 190 likes
  • 211 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install zero-shot-image-segmentation-sam

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent installs SAM, picks the checkpoint that fits (ViT-H, ViT-L or ViT-B) and generates masks from points or boxes. You get masks for annotation or a vision pipeline.

Mostly picked by

Updated November 2, 2026

Card for the “Segment images without training using SAM” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: use cases, installation and checkpoint choice
  • references/: advanced usage and troubleshooting

Good fit for

  • You need to annotate objects in photos quickly without training a model
  • You are building a tool where the user clicks the object to isolate

Not for

    Tags

    • segmentation
    • sam
    • vision
    • masks
    • annotation

    About

    You say

    “Segment the car in this photo from one click and give me the mask.”

    Card for the “Segment images without training using SAM” skill

    Skill published by Orchestra Research under the MIT license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to segment objects in images, without training, using SAM
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/advanced-usage.md15.4 KB
    • references/troubleshooting.md11.6 KB
    • SKILL.md13 KB

    Origin and licence

    Listed unmodified

    Author
    Orchestra Research
    Source
    github.com/nousresearch/hermes-agent/tree/0c74cc682dc81bf78b78a1737b3ee77a820ccb79/optional-skills/mlops/models/segment-anything-model
    Licence
    MIT

    Notice

    « segment-anything-model » (Orchestra Research, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.