Luma
Video modification and transformation powered by Luma's Dream Machine model.
# Works with Claude Code, Codex, Gemini CLI, Cursor, and 50+ agents
npx skills add runapi-ai/luma -gInstall the Luma skill for me: 1. Clone https://github.com/runapi-ai/luma 2. Copy the skills/luma/ directory into your user-level skills directory (e.g. ~/.claude/skills/ for Claude Code, ~/.codex/skills/ for Codex). 3. Verify that SKILL.md is present. 4. Confirm the install path when done.
Luma Dream Machine's video modification model retransforms existing footage with new visual styles or scene changes while preserving the source clip's motion and temporal structure.
- Installable agent skill
- Unified API key
- SDK examples included
- 失敗した生成は課金されません
料金
仕様
| Model ID | luma-modify-video |
| プロバイダー | Luma |
| モダリティ | video |
| Task type | asynchronous |
| 課金 | call |
| Endpoint | /api/v1/luma/modify_video |
| Commercial | Yes |
| Status | Operational |
Use this model from your agent
# User prompt to the agent
"Transform this office walkthrough video into a cyberpunk aesthetic with neon lighting, keeping the original camera movement."// Code generated by the agent via @runapi.ai/luma
import { LumaClient } from '@runapi.ai/luma';
const client = new LumaClient();
const result = await client.modifyVideo.run({
model: 'luma-modify-video',
prompt: 'Transform this office walkthrough video into a cyberpunk aesthetic with neon lighting, keeping the original camera movement.',
});How to call this model
Install the skill
Add the model skill to your agent or install the SDK package.
Authenticate once
Use your RunAPI key for every supported model.
Send a request
Use the unified schema for the endpoint you need.
Receive output
Poll by task ID or handle the callback when the generation completes.
SDK quickstart
curl -X POST https://runapi.ai/api/v1/luma/modify_video \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "luma-modify-video",
"video_url": "https://cdn.runapi.ai/public/samples/video.mp4",
"prompt": "Transform this office walkthrough video into a cyberpunk aesthetic with neon lighting, keeping the original camera movement."
}'import { LumaClient } from "@runapi.ai/luma";
const client = new LumaClient();
const result = await client.modifyVideo.run({
model: "luma-modify-video",
video_url: "https://cdn.runapi.ai/public/samples/video.mp4",
prompt: "Transform this office walkthrough video into a cyberpunk aesthetic with neon lighting, keeping the original camera movement.",
});require "runapi/luma"
client = RunApi::Luma::Client.new
result = client.modify_video.run(
model: "luma-modify-video",
video_url: "https://cdn.runapi.ai/public/samples/video.mp4",
prompt: "Transform this office walkthrough video into a cyberpunk aesthetic with neon lighting, keeping the original camera movement."
)Where Luma fits
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.
Why use Luma through RunAPI
One API key
Use the same credentials across models and providers.
Agent-ready
Installable skills include docs and schema for tool calls.
Predictable billing
Usage-based pricing is visible before you call.
Frequently asked questions
How do I call this model?
Use the RunAPI SDK, CLI, or REST endpoint shown on this page.
Do failed generations cost money?
失敗した生成は課金されません
Can agents use it directly?
Yes. Install the model skill and your agent gets the docs, schema, and examples.
