Luma Video

Generate AI videos with Luma Dream Machine via AceDataCloud API. Use when creating videos from text prompts, generating videos from reference images, extendi...

Security Scan

The skill is an instruction-only wrapper for AceDataCloud's Luma Dream Machine API and mostly coherent, but registry metadata omits the ACEDATACLOUD_API_TOKEN requirement and the publisher/source is unverified — verify before using.

Purpose & Capability

The SKILL.md clearly requires an ACEDATACLOUD_API_TOKEN to call https://api.acedata.cloud, which is coherent with the stated purpose. However, the registry metadata lists no required environment variables or primary credential — that mismatch is an integrity problem (metadata understates what will be needed).

Instruction Scope

Runtime instructions are limited to calling the AceDataCloud Luma endpoints (curl POSTs) and optionally installing/using a separate mcp-luma helper. The doc does not instruct reading unrelated files, broad system state, or other env vars. It does expect public image URLs for image-to-video workflows.

Install Mechanism

There is no install spec and no code files (lowest disk-write risk). The doc suggests optionally running `pip install mcp-luma` or using a hosted MCP server — installing a third-party pip package introduces typical supply-chain risk and should be reviewed, but the skill itself does not auto-install anything.

Credentials

The SKILL.md requires a single API token (ACEDATACLOUD_API_TOKEN), which is proportional for a cloud API integration. The concern is that the registry metadata incorrectly lists no required env vars or primary credential — this inconsistency can hide the fact that a secret is needed and transmitted to api.acedata.cloud.

Persistence & Privilege

The skill is instruction-only, does not request persistent installation, and 'always' is false. It does allow normal autonomous invocation (platform default), but there is no indication it modifies other skills or system settings.

What to consider before installing

This skill appears to be a straightforward set of instructions for calling AceDataCloud's Luma API, but there are two things to check before you use it: (1) the SKILL.md requires an ACEDATACLOUD_API_TOKEN even though the registry metadata omits that — ensure you only supply a token you obtained from a trusted AceDataCloud source and that the token has least privilege; (2) the skill is from an unknown/unnamed source and references a domain (api.acedata.cloud) and an optional pip package (mcp-luma) — verify the vendor, review the pip package code or its official repository, and confirm pricing/privacy terms. Also be aware that image-to-video mode requires publicly accessible image URLs (which can expose those images), and any API calls will transmit your prompt and referenced URLs to the AceDataCloud service. If you cannot verify the publisher or the package, treat the token as sensitive and avoid reuse of high-privilege credentials.

Luma Video Generation

Generate AI videos through AceDataCloud's Luma Dream Machine API.

Authentication

export ACEDATACLOUD_API_TOKEN="your-token-here"

Quick Start

curl -X POST https://api.acedata.cloud/luma/videos \
  -H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"prompt": "a drone flying over a mountain lake at sunrise", "action": "generate", "wait": true}'

Workflows

1. Text-to-Video

Generate video purely from a text description.

POST /luma/videos
{
  "prompt": "a timelapse of flowers blooming in a garden",
  "action": "generate",
  "aspect_ratio": "16:9",
  "loop": false,
  "enhancement": true
}

2. Image-to-Video

Use start and/or end reference images to guide generation.

POST /luma/videos
{
  "prompt": "the scene comes alive with gentle wind",
  "action": "generate",
  "start_image_url": "https://example.com/scene.jpg",
  "end_image_url": "https://example.com/scene-end.jpg",
  "aspect_ratio": "16:9"
}

3. Extend a Video

Continue an existing video with a new prompt.

POST /luma/videos
{
  "action": "extend",
  "video_id": "existing-video-id",
  "prompt": "the camera continues forward through the forest"
}

Aspect Ratios

Ratio	Use Case
16:9	Landscape (default) — YouTube, TV
9:16	Portrait — TikTok, Instagram Stories
1:1	Square — Social media
4:3	Classic — Presentations
21:9	Ultra-wide — Cinematic

Parameters

Parameter	Type	Default	Description
prompt	string	—	Text description of the video (required)
action	string	"generate"	"generate" or "extend"
aspect_ratio	string	"16:9"	Video aspect ratio
loop	bool	false	Create seamless loop
enhancement	bool	true	Enhance prompt for better results
start_image_url	string	—	Reference image for first frame
end_image_url	string	—	Reference image for last frame
video_id	string	—	Required for extend action

Task Polling

POST /luma/tasks
{"task_id": "your-task-id"}

Poll every 5 seconds. States: pending → completed or failed.

MCP Server

pip install mcp-luma

Or hosted: https://luma.mcp.acedata.cloud/mcp

Key tools: luma_generate_video, luma_generate_video_from_image, luma_extend_video

Gotchas

• enhancement: true (default) improves prompt quality but may alter your intent — set to false for literal prompts
• Start/end image URLs must be publicly accessible
• loop: true creates seamless looping video — good for backgrounds and social media
• Extend requires the video_id from a previously completed generation
• Video generation takes 1–5 minutes depending on complexity
• Both start and end images are optional — you can use just one for partial guidance