--- title: Use Luma in WorkBuddy via RunAPI — Video MCP Guide | RunAPI description: Modify video with Luma Ray 3.2 in WorkBuddy through the RunAPI MCP server. Prompt-driven transformations with spatial coherence, one API key. url: https://runapi.ai/workbuddy-luma.md canonical: https://runapi.ai/workbuddy-luma locale: en site: RunAPI image: https://runapi.ai/assets/opengraph-bfaaa0f0.png alternates: en: https://runapi.ai/workbuddy-luma zh-CN: https://runapi.ai/zh-CN/workbuddy-luma es: https://runapi.ai/es/workbuddy-luma ja: https://runapi.ai/ja/workbuddy-luma de: https://runapi.ai/de/workbuddy-luma fr: https://runapi.ai/fr/workbuddy-luma pt-BR: https://runapi.ai/pt-BR/workbuddy-luma ko: https://runapi.ai/ko/workbuddy-luma it: https://runapi.ai/it/workbuddy-luma nl: https://runapi.ai/nl/workbuddy-luma pl: https://runapi.ai/pl/workbuddy-luma tr: https://runapi.ai/tr/workbuddy-luma zh-TW: https://runapi.ai/zh-TW/workbuddy-luma zh-HK: https://runapi.ai/zh-HK/workbuddy-luma ar: https://runapi.ai/ar/workbuddy-luma x-default: https://runapi.ai/workbuddy-luma model: luma --- > HTML version: https://runapi.ai/workbuddy-luma > Site index for agents: https://runapi.ai/llms.txt # Use Luma in WorkBuddy. Luma Ray 3.2 modifies existing video with prompt-driven transformations that preserve spatial coherence and 3D scene structure. WorkBuddy speaks MCP natively — add RunAPI as an MCP server once, then hand the workbench agent a source video URL and describe the transformation. It calls the Luma tool, waits for the async task, and returns the re-rendered video with atmospheric lighting and physically consistent camera motion. - [Get API Key](https://runapi.ai/login) - [Read the docs](https://runapi.ai/docs/guides) one MCP server · one RunAPI key · async task handling ### Prompt ```text Modify a video with Luma Ray 3.2 through the runapi MCP server. Requirements: - Use the runapi MCP server's video modification tool. - Set model to "luma-modify-video". - Source video: https://example.com/park-walk.mp4 - Transformation: "Transform the scene into a foggy autumn morning with golden light filtering through trees". - The task is async — wait for it to complete and give me the modified video URL. ``` ### MCP config ```bash { "mcp_servers": { "runapi": { "url": "https://runapi.ai/mcp", "transport": "streamable_http", "headers": { "Authorization": "Bearer $RUNAPI_API_KEY" } } } } ``` ### Response ```json { "task_id": "tsk_abc123", "status": "completed", "model": "luma-modify-video", "output": { "video_url": "https://media.runapi.ai/videos/tsk_abc123.mp4" } } ``` ## Use Luma in WorkBuddy in three steps 1. **Add the RunAPI MCP server** - Register RunAPI as an MCP server named runapi pointing at https://runapi.ai/mcp, with the Authorization header reading your key from RUNAPI_API_KEY. If you already connected RunAPI to WorkBuddy, the same server exposes the Luma tool — no extra setup needed. `{ "mcp_servers": { "runapi": { "url": "https://runapi.ai/mcp", "transport": "streamable_http", "headers": { "Authorization": "Bearer $RUNAPI_API_KEY" } } } } ` 2. **Prompt the workbench agent** - Give WorkBuddy a source video URL and describe the transformation in plain language — atmosphere, lighting, style, or scene edits. The agent maps your request onto the Luma modify_video tool with model set to luma-modify-video, and Luma preserves the original scene geometry while applying the changes. `Restyle https://example.com/park-walk.mp4 with Luma: a foggy autumn morning with golden light filtering through trees. ` 3. **Receive the modified video** - The Luma task is asynchronous. WorkBuddy polls it through the MCP server until the status is completed, then posts the re-rendered video URL into your conversation. Typical processing takes 30-120 seconds depending on complexity. `{ "task_id": "tsk_abc123", "status": "completed", "output": { "video_url": "https://media.runapi.ai/videos/tsk_abc123.mp4" } } ` ## Luma modify_video tool parameters | Parameter | Type | Description | | --- | --- | --- | | `model` | `string` | Required. Use luma-modify-video. | | `prompt` | `string` | Required. Text description of the desired video transformation — style changes, lighting, atmosphere, or scene edits. | | `source_video_url` | `string` | Required. URL of the source video to modify. Must be a publicly accessible MP4 or MOV file. | | `watermark` | `boolean` | Optional. Whether to add a watermark to the output video. | | `callback_url` | `string` | Optional. Webhook URL that receives a POST when the task completes. | | `task_id` | `string` | Returned by the tool. WorkBuddy uses it to poll the async task until the modified video is ready. | ## What is Luma on WorkBuddy? Luma Ray 3.2 (Dream Machine) specializes in modifying existing video with a dreamlike quality that users describe as cinematic-looking and fast to iterate with. Rather than generating from scratch, it re-renders source footage with prompt-driven transformations — atmospheric shifts, style conversions, and environmental changes — while keeping the original spatial layout and camera motion intact. WorkBuddy reaches it through the runapi MCP server, the same server and RUNAPI_API_KEY that power every other model in the workbench. ## Luma use cases - **Mood pieces and music video aesthetics** - Ask WorkBuddy to transform raw footage into stylized mood pieces with Luma's dreamlike visual quality. Change lighting, atmosphere, and color palette while preserving the original motion for music video concepts or art projects. - **Quick visual hypotheses for ad directions** - Restyle an existing product video in multiple visual directions — cinematic, minimal, noir, or seasonal — from a single workbench conversation, to test which look works before committing to a full reshoot. - **Base footage for multi-tool pipelines** - Use Luma to restyle generated or shot footage, then let WorkBuddy pass the result to other RunAPI tools in the same session. Luma's fast turnaround makes it practical as a styling step in a larger video pipeline. ## Luma + WorkBuddy questions ### What kind of transformations can Luma do in WorkBuddy? Luma modify_video re-renders existing footage with prompt-driven changes — atmospheric shifts (fog, rain, golden hour), style transfers (cinematic, anime, noir), lighting overhauls, and environmental transformations. It preserves the original camera motion and spatial layout, and WorkBuddy drives it all from a plain-language prompt. ### How is Luma different from other video models on RunAPI? Luma specializes in modifying existing video rather than generating from scratch. Its Ray 3.2 model maintains 3D spatial coherence during transformations, so objects keep their depth relationships and camera motion stays physically consistent. Models like Kling or Hailuo generate new video from text or images — all reachable from the same runapi MCP server. ### Does WorkBuddy wait for the result, or do I poll myself? The workbench agent handles it. Luma tasks are asynchronous — the tool returns a task_id, and WorkBuddy polls the task through the MCP server until the status is completed, then posts the modified video URL into your conversation. Typical processing time is 30-120 seconds. ### What does Luma video modification cost on RunAPI? Luma uses flat per-task billing — each modify_video call costs a fixed amount regardless of video length. Check the RunAPI pricing page for current rates. Failed generations are not charged. ### Can I chain Luma with other RunAPI video models in one WorkBuddy session? Yes. Ask WorkBuddy to generate a video with Kling or Hailuo, then pass the output URL as source_video_url to Luma modify_video for post-processing — all through the same runapi MCP server and RUNAPI_API_KEY, in a single conversation. - [WorkBuddy setup guide →](https://runapi.ai/workbuddy.md) - Not connected yet? Start with the RunAPI MCP setup guide for WorkBuddy. - [Luma on RunAPI →](https://runapi.ai/models/luma.md) - See Luma variants, pricing, and API docs. ## Try Luma in WorkBuddy today. Get a free RunAPI key, add the MCP server to WorkBuddy, and start modifying video with Luma Ray 3.2 spatial-aware transformations without leaving the workbench. [Browse models →](https://runapi.ai/models.md) --- ## More from RunAPI - [Home](https://runapi.ai/.md) ### Product - [Model Catalog](https://runapi.ai/models.md) - [Pricing](https://runapi.ai/pricing.md) - [Providers](https://runapi.ai/models#all-models) ### Developers - [Documentation](https://runapi.ai/docs/guides) - [SDKs](https://runapi.ai/sdk.md) - [CLI](https://runapi.ai/cli.md) - [MCP Server](https://runapi.ai/mcp.md) - [x402](https://runapi.ai/x402.md) ### Guides - [Claude Code vs Cursor](https://runapi.ai/claude-code-vs-cursor.md) - [Cursor API Setup](https://runapi.ai/cursor-api-setup.md) - [RunAPI vs OpenRouter](https://runapi.ai/openrouter-alternative.md) ### Company - [Enterprise](https://runapi.ai/contact.md) - [Contact](https://runapi.ai/contact.md) ### Legal - [Terms](https://runapi.ai/terms.md) - [Privacy](https://runapi.ai/privacy.md) - [Site index for agents](https://runapi.ai/llms.txt) Contact: contact@runapi.ai ## Structured data ```json [ { "@context": "https://schema.org", "inLanguage": "en", "@type": "WebSite", "name": "RunAPI", "url": "https://runapi.ai/", "potentialAction": { "@type": "SearchAction", "target": { "@type": "EntryPoint", "urlTemplate": "https://runapi.ai/models?q={search_term_string}" }, "query-input": "required name=search_term_string" } }, { "@context": "https://schema.org", "inLanguage": "en", "@type": "Organization", "name": "RunAPI", "url": "https://runapi.ai/", "logo": { "@type": "ImageObject", "url": "https://runapi.ai/icon.svg" }, "sameAs": [ "https://github.com/runapi-ai" ] }, { "@context": "https://schema.org", "inLanguage": "en", "@type": "SoftwareApplication", "name": "RunAPI Luma for WorkBuddy", "applicationCategory": "DeveloperApplication", "description": "Modify video with Luma Ray 3.2 in WorkBuddy through the RunAPI MCP server. Prompt-driven transformations with spatial coherence, one API key.", "url": "https://runapi.ai/workbuddy-luma" }, { "@context": "https://schema.org", "inLanguage": "en", "@type": "FAQPage", "mainEntity": [ { "@type": "Question", "name": "What kind of transformations can Luma do in WorkBuddy?", "acceptedAnswer": { "@type": "Answer", "text": "Luma modify_video re-renders existing footage with prompt-driven changes — atmospheric shifts (fog, rain, golden hour), style transfers (cinematic, anime, noir), lighting overhauls, and environmental transformations. It preserves the original camera motion and spatial layout, and WorkBuddy drives it all from a plain-language prompt." } }, { "@type": "Question", "name": "How is Luma different from other video models on RunAPI?", "acceptedAnswer": { "@type": "Answer", "text": "Luma specializes in modifying existing video rather than generating from scratch. Its Ray 3.2 model maintains 3D spatial coherence during transformations, so objects keep their depth relationships and camera motion stays physically consistent. Models like Kling or Hailuo generate new video from text or images — all reachable from the same runapi MCP server." } }, { "@type": "Question", "name": "Does WorkBuddy wait for the result, or do I poll myself?", "acceptedAnswer": { "@type": "Answer", "text": "The workbench agent handles it. Luma tasks are asynchronous — the tool returns a task_id, and WorkBuddy polls the task through the MCP server until the status is completed, then posts the modified video URL into your conversation. Typical processing time is 30-120 seconds." } }, { "@type": "Question", "name": "What does Luma video modification cost on RunAPI?", "acceptedAnswer": { "@type": "Answer", "text": "Luma uses flat per-task billing — each modify_video call costs a fixed amount regardless of video length. Check the RunAPI pricing page for current rates. Failed generations are not charged." } }, { "@type": "Question", "name": "Can I chain Luma with other RunAPI video models in one WorkBuddy session?", "acceptedAnswer": { "@type": "Answer", "text": "Yes. Ask WorkBuddy to generate a video with Kling or Hailuo, then pass the output URL as source_video_url to Luma modify_video for post-processing — all through the same runapi MCP server and RUNAPI_API_KEY, in a single conversation." } } ] }, { "@context": "https://schema.org", "inLanguage": "en", "@type": "HowTo", "name": "How to use Luma in WorkBuddy via RunAPI", "description": "Add RunAPI as an MCP server in WorkBuddy, hand the workbench agent a source video and a transformation prompt, and receive the re-rendered Luma Ray 3.2 result.", "step": [ { "@type": "HowToStep", "position": 1, "name": "Add the RunAPI MCP server", "text": "Register RunAPI as an MCP server named runapi pointing at https://runapi.ai/mcp, with the Authorization header reading your key from RUNAPI_API_KEY. If you already connected RunAPI to WorkBuddy, the same server exposes the Luma tool — no extra setup needed.", "url": "https://runapi.ai/workbuddy-luma#how-step-1" }, { "@type": "HowToStep", "position": 2, "name": "Prompt the workbench agent", "text": "Give WorkBuddy a source video URL and describe the transformation in plain language — atmosphere, lighting, style, or scene edits. The agent maps your request onto the Luma modify_video tool with model set to luma-modify-video, and Luma preserves the original scene geometry while applying the changes.", "url": "https://runapi.ai/workbuddy-luma#how-step-2" }, { "@type": "HowToStep", "position": 3, "name": "Receive the modified video", "text": "The Luma task is asynchronous. WorkBuddy polls it through the MCP server until the status is completed, then posts the re-rendered video URL into your conversation. Typical processing takes 30-120 seconds depending on complexity.", "url": "https://runapi.ai/workbuddy-luma#how-step-3" } ] }, { "@context": "https://schema.org", "inLanguage": "en", "@type": "BreadcrumbList", "itemListElement": [ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://runapi.ai/" }, { "@type": "ListItem", "position": 2, "name": "RunAPI Luma for WorkBuddy", "item": "https://runapi.ai/workbuddy-luma" } ] } ] ```