Video · Luma

Luma API

Video modification and transformation powered by Luma's Dream Machine model.

可正常運作 · 1 endpoints · 由 $0.500

runapi.ai

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.",
});

<?php

require __DIR__ . "/vendor/autoload.php";

use RunApi\Luma\LumaClient;

$client = new LumaClient();
$result = $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."
)

npx skills add runapi-ai/luma -g

# Claude Code
claude mcp add runapi -s user -- npx -y @runapi.ai/mcp

# Codex
codex plugin install runapi-mcp@agents

# Cursor / Windsurf / VS Code
npx @runapi.ai/mcp init cursor

@runapi.ai/luma v1

OVERVIEW

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.

多個變體，對應不同速度／品質層級
Model skill 包含文件、schema 與 setup 備註
支援 app-focused coding workflows
生成失敗不收費

PRICING

收費

失敗的生成不會收費

Modify video

$0.50 / video

規格說明

技術詳情

模型 ID	luma-modify-video
供應商	Luma
模式	video
任務類型	asynchronous
計費單位	call
API endpoint	/api/v1/luma/modify_video
商業授權	是 — 已透過 API 包含
目錄狀態	可正常運作

SKILLS

為 app 開發安裝 Luma skill

將模型文件、schema、價格備註與 setup 步驟載入 coding workspace。

# Install the model skill for app development workflows
npx skills add runapi-ai/luma -g

Installs docs, schemas, pricing context, and setup notes into your developer workspace.

Or use this setup request in your coding tool:

Install the Luma skill for this app:

1. Add runapi-ai/luma with the skills installer.
2. Load SKILL.md in this workspace.
3. Use its docs, schemas, pricing notes, and setup steps when adding model features.
4. Confirm the install path when done.

OpenClaw

Use Luma in OpenClaw

Prompt, curl command, parameters, and FAQ.

Hermes Agent

Use Luma in Hermes Agent

Custom provider setup, API call, and FAQ.

運作方式

從 model skill 到第一次結果，只需四步

選擇模型

挑選符合輸出類型、品質門檻與延遲目標的模型與變體。

設定

設定 RunAPI key，並在 coding workspace 安裝 model skill。

開發

使用 skill 指引，在你的 app 內加入模型功能。

接收

透過 task ID 查詢、在支援時串流，或處理 webhook callback。

CONTEXT

Luma API 是甚麼？

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.

Provider

Luma

Modality

Video

點解揀 RunAPI

為何透過 RunAPI 使用 Luma API

一個驗證，對應所有 provider

一組 RunAPI key 即可解鎖整個 catalog。無需分開帳戶，亦無需為每個整合輪換密鑰。

統一定價與計費

按次以 USD 收費，每月結算。失敗的生成不會收費。

內含 schema 的 skill

型別化 schema 與 setup 備註打包在 model skill 內，讓實作從正確契約開始。

FAQ

常見問題

What is video modification?

Luma's modify-video endpoint takes existing footage and retransforms its visual style and content based on a text prompt, while preserving the original motion and camera dynamics.

Does it preserve the original motion?

Yes — camera movement, subject motion, and temporal structure from the source video are maintained. Only the visual style and appearance change.

What styles can I apply?

Any style describable in text — cinematic, anime, painterly, noir, retro, futuristic, and more. The prompt controls the transformation direction.

What input video formats are supported?

MP4 is the primary supported format. Source clips should be within the size and duration limits specified in the API docs.

How does Luma compare to Runway Aleph?

Both transform existing footage from prompts. Luma focuses on style transfer via the Dream Machine architecture. Runway Aleph emphasizes frame-level continuity preservation.

我應該先用邊個版本？

先選最平而且符合你質素要求的版本。大多數團隊會先用快速版本，之後再升級到 pro 用於正式生產。

有免費方案嗎？

新帳戶可獲得每個模型的首次呼叫免費。之後按次收費。

你哋支援串流結果嗎？

如有提供串流，RunAPI 會端到端串流。

失敗會點樣收費？

生成失敗不會收費。

輸出有快取嗎？

已生成輸出會儲存，並可按任務 ID 取回。輸入內容不會快取。

可以商業使用嗎？

可以——除非模型授權明確限制，否則每個版本都包括商業使用。相關限制會在版本頁面列明。