Atlas Cloud Media

Use the bundled scripts/atlas_media.py CLI to discover current Atlas Cloud models, inspect a model's live request schema, and run asynchronous image or video generation.

When to Use This Skill

• The user wants to find an available Atlas Cloud image or video model.
• An integration needs the current model ID, input fields, endpoint, or price.
• The user wants one explicitly confirmed media generation request.
• An asynchronous Atlas Cloud task needs bounded status polling.

Setup

Set the API key in the environment. Never pass it as a CLI argument or commit it to a repository.

export ATLASCLOUD_API_KEY="your-api-key"

ATLASCLOUD_BASE_URL may point to a compatible deployment. It defaults to https://api.atlascloud.ai.

Workflow

1. Discover current models

python3 scripts/atlas_media.py models --type Image --query flux
python3 scripts/atlas_media.py models --type Video --query seedance

Treat model availability and prices as live data. Run discovery immediately before choosing a model.

2. Inspect the exact schema

python3 scripts/atlas_media.py describe black-forest-labs/flux-schnell

The command resolves the model's current schema URL and reports the required fields, property definitions, submission endpoint, result endpoint, and catalog price data. Build the payload from this output instead of copying an old example.

3. Prepare parameters in a file

{
  "prompt": "A clean product photograph on a neutral background",
  "size": "1024*1024",
  "num_images": 1
}

Do not include model; the CLI inserts the selected model ID after validation.

4. Confirm cost and generate once

python3 scripts/atlas_media.py generate \
  black-forest-labs/flux-schnell \
  --params-file request.json \
  --confirm-paid