Luma · Video

OpenClaw x Luma

Luma AI's Dream Machine model modifies existing video by retransforming visual style while preserving motion. Through RunAPI, it shares unified API access and per-call billing.

1 variants from $0.50 / call Commercial OK

Prerequisite: npx runapi mcp install

Prompt

Prompt models

Use luma-modify-video when it matches the task: luma-modify-video.

You have access to RunAPI task tools for Luma.

Available Luma models:
- luma-modify-video: luma-modify-video
  endpoints: /api/v1/luma/modify_video
  request fields: model, prompt, source_video_url

Use the model ID and endpoint that match the user's request.
Example prompt: Transform this office walkthrough video into a cyberpunk aesthetic with neon lighting, keeping the original camera movement.
/api/v1/luma/modify_video: Submit the task, poll for its status, then verify the completed output. POST /api/v1/luma/modify_video and save the returned Task id.
GET /api/v1/luma/modify_video/<task-id> until status is completed or failed.
Verify the completed response contains the endpoint-specific output documented in the API reference.

Public Versions and Endpoints

Model ID Endpoints Price Catalog
luma-modify-video
/api/v1/luma/modify_video
$0.50 / call Model detail

Verify

Poll until the task reaches a terminal status

POST /api/v1/luma/modify_video and save the returned Task id.
GET /api/v1/luma/modify_video/<task-id> until status is completed or failed.
Verify the completed response contains the endpoint-specific output documented in the API reference.

Configuration

Guide endpoint: /api/v1/luma/modify_video

export RUNAPI_API_KEY=your_api_key

curl -X POST https://runapi.ai/api/v1/luma/modify_video \
  -H "Authorization: Bearer $RUNAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "luma-modify-video",
  "prompt": "Add a warm golden-hour look.",
  "source_video_url": "https://file.runapi.ai/source-video.mp4"
}'
How it works

Get Started in 3 Steps

  1. Choose a model ID

    Select a public catalog model ID and review its endpoint and current starting price.

  2. Configure RunAPI

    Set RUNAPI_API_KEY before making the endpoint request.

  3. Verify the result

    For asynchronous endpoints, poll the same endpoint until the Task reaches a terminal status.

What to Build with OpenClaw + Luma

  • Mood pieces and music video aesthetics

    Transform raw footage into stylized mood pieces, changing lighting, atmosphere, and color while keeping the original motion.

  • Quick visual tests for ad directions

    Restyle an existing product video in several visual directions to test which look works before a reshoot.

  • Styling step in multi-tool pipelines

    Use Luma to restyle generated or filmed footage, then pass it to other tools for final editing.

Why Use Luma Through RunAPI + OpenClaw

  • 1 variants, one API key

    Use one RunAPI connection to choose among the live model variants without changing your integration.

  • Clear usage pricing

    See current catalog pricing before you send a request, with no subscription or minimum spend required.

  • Automatic task workflows

    Submit, poll, and collect asynchronous results through a consistent task workflow without writing manual polling code.

OpenClaw + Luma Questions

What kinds of changes can Luma make to a video?

Luma re-renders existing footage with prompt-driven changes such as weather, time of day, style transfer, and lighting, while preserving the original camera motion and layout.

How is Luma different from other video models on RunAPI?

Luma modifies existing video instead of generating from scratch, and it keeps the spatial layout of the scene consistent during the transformation.

Can I chain Luma with other RunAPI video models in OpenClaw?

Yes. An OpenClaw agent can generate a clip with another video model, then pass the output URL to Luma for restyling, all with the same RunAPI API key.

Which model ID should I use?

Choose a public model ID from the version table. Each ID exposes the endpoints shown for that version.

Does this guide configure a chat model?

No. This Model Line uses the endpoint workflow shown here and is not presented as an agent chat model.

Start using Luma with OpenClaw

Building with a team?

We're here to help with enterprise setup, integrations, and technical questions.

Contact Us