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.

TAO AnomalyGen pipeline: fine-tuning and anomaly images v1.0.0

Use this resource to generate synthetic anomaly images with the TAO AnomalyGen pipeline

New

  • 514 downloads
  • 132 likes
  • 113 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install anomaly-image-generation-pipeline

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 runs the pipeline phases for the chosen mode (full, fine-tuning only or generation only), checks the checkpoints and evaluates quality with the nn score. You get synthetic anomaly images and their evaluation.

Mostly picked by

Updated November 2, 2026

Card for the “TAO AnomalyGen pipeline: fine-tuning and anomaly images” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
Apache-2.0

Similar resources

View all

What you get

  • SKILL.md: phases, modes and parameters
  • references/datasets.md: dataset formats
  • references/finetune.md: fine-tuning procedure

Good fit for

  • You have few anomaly images and want to generate more
  • You want to evaluate the quality of a synthetic generation

Not for

    Tags

    • anomalies
    • synthetic images
    • tao
    • generation

    About

    You say

    “Generate anomaly images from my existing AnomalyGen checkpoint.”

    Card for the “TAO AnomalyGen pipeline: fine-tuning and anomaly images” skill

    Skill published by nvidia under the Apache-2.0 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 generate synthetic anomaly images with the TAO AnomalyGen pipeline
    3. Review and adjust the result

    Content preview

    Files

    • assets/ag_config.yaml1.4 KB
    • assets/defect_spec_template.jsonl0.5 KB
    • BENCHMARK.md7.9 KB
    • config/skillspector-baseline.yaml1.7 KB
    • evals/evals.json0.8 KB
    • LICENSE11.3 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/datasets.md5 KB
    • references/docker.md3.6 KB
    • references/error-handling.md1.9 KB
    • references/eval.md7.6 KB
    • references/finetune-commands.md2.3 KB
    • references/finetune.md8.4 KB
    • references/guard-and-custom-counts.md2 KB
    • references/inference-commands.md1.4 KB
    • references/inference.md15.3 KB
    • references/output-layout.md3.9 KB
    • references/prep-testcase.md7.7 KB
    • references/sdg-inference.md4.9 KB
    • references/sdg-refine.md5 KB
    • references/setup.md4.1 KB
    • skill-card.md5.6 KB
    • SKILL.md19.5 KB
    • skill.oms.sig8.5 KB

    Origin and licence

    Listed unmodified

    Author
    nvidia
    Source
    github.com/nvidia/skills/tree/ca116d60beafe1b4459f0ab790b7b450912c56b0/skills/tao-generate-anomalies
    Licence
    Apache-2.0

    Notice

    « tao-generate-anomalies » (nvidia, Apache-2.0) 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.