Grok Video Gen

Generate videos using xAI Grok.

Overview

Grok Video Gen submits a video generation job to xAI Grok Imagine from a text prompt, with an optional starting image for image-to-video. By default it then polls until the job is done and downloads the finished video, storing it on the output item as binary data. Set Wait For Completion off to return the job ID straight away and pick the result up later.

Category: AI
Tool Name: grok_video_gen
Version: 1

Appearance: Icon: brain | Color: #000000

Node Type

Action (Binary) — handles file/binary data operations

Input / Output

Direction	Port(s)
Input	Input
Output	Output, Error

Credentials

This tool requires xAI credentials. See the Credentials Guide for setup instructions.

Parameters

Parameter	Type	Required	Default	Description
Model	options	No	Platform default	The video generation model to use.
				Options: the Grok Imagine video models currently available — the dropdown tracks the model catalog, so it changes as xAI’s line-up changes.
Prompt	string	Yes	—	Text prompt describing the video to generate. Supports expressions like {{ $json.description }}. Falls back to the input item’s “prompt”, “text” or “description” field when left empty.
Options	collection	No	{}	Optional generation, polling and output settings — add only the fields you want to override.
— Input Image URL (image-to-video)	string	No	—	Optional. A still image URL (or base64 data URL) to use as the video’s starting frame (image-to-video). Supports expressions. Required for grok-imagine-video-1.5-preview (image-to-video only). Leave empty for text-to-video on grok-imagine-video.
— Input Image Binary Property (image-to-video)	string	No	—	Optional. Name of an upstream binary property holding an image to use as the starting frame. Used only when Input Image URL is empty. Check the upstream node’s Binary Data panel for the exact name (often “data”).
— Duration	options	No	5	Duration of the generated video in seconds (xAI accepts an integer, max 15).
				Options: 5, 10, 15
— Wait For Completion	boolean	No	true	Whether to poll until the video generation is complete. If false, returns the job ID immediately.
— Poll Interval (ms)	number	No	10000	Milliseconds between poll requests when waiting for completion.
— Max Poll Duration (ms)	number	No	600000	Maximum total time to spend polling before timing out (default: 10 minutes).
— Binary Property Name	string	No	data	Property name for the primary video binary output. Additional videos use video_1, video_2, etc. Names are case-sensitive — see the upstream node’s Binary Data panel for the exact names to use.
— Response Field Name	string	No	video	Output field name for the API response data.
Include Input	boolean	No	false	Whether to include the original input item fields in the output.
Max Concurrency	number	No	3	Maximum number of items to process concurrently. Keep low for video generation due to heavy resource usage.

Output Data

One output item per input item. The rest of the input JSON is carried over only when Include Input is on.

• jobId — the generation job’s ID, whether or not the node waited for it.
• model — the model the job was submitted to.
• status — the job status. pending when Wait For Completion is off; otherwise the terminal status the job reached.
• video — the job record, under whatever name Response Field Name is set to. When the node waited, this is the full job response; when it did not, it is { "id": "<jobId>", "status": "pending" }.

When the node waits and the job finishes successfully, the finished video is downloaded and attached to the output item as binary data under the name given by Binary Property Name (data by default). If the job returns more than one video, the extras land under video_1, video_2, and so on. Any binary the input item already carried is preserved.

Reference the result downstream by expression, e.g. {{ $json.jobId }} or {{ $json.status }}.

Usage Examples

• Generate a video of a space scene using Grok
• Create a portrait-format video for a social media story
• Generate a video from a text description
• Create a landscape video with a cinematic prompt
• Generate a short social-media clip by describing the framing in the prompt

Example Configuration

Generate a short video and wait for it:

{
  "type": "grok_video_gen",
  "parameters": {
    "prompt": "A timelapse of a city skyline at sunset with dramatic clouds"
  }
}

Portrait video from an item field, with a longer polling budget:

{
  "type": "grok_video_gen",
  "parameters": {
    "prompt": "{{ $json.description }}",
    "includeInput": true,
    "maxConcurrency": 1,
    "options": {
      "duration": 10,
      "waitForCompletion": true,
      "pollIntervalMs": 15000,
      "maxPollDurationMs": 1200000,
      "binaryPropertyName": "videoFile"
    }
  }
}

Animate an upstream image (image-to-video):

{
  "type": "grok_video_gen",
  "parameters": {
    "prompt": "Slow push-in with gentle camera drift",
    "options": {
      "inputBinaryPropertyName": "data",
      "duration": 5
    }
  }
}

Submit without waiting and capture the job ID for a later step:

{
  "type": "grok_video_gen",
  "parameters": {
    "prompt": "An abstract swirling galaxy forming from stardust",
    "maxConcurrency": 3,
    "options": {
      "duration": 10,
      "waitForCompletion": false,
      "responseFieldName": "jobInfo"
    }
  }
}

Error Handling

Mode	Behavior
stop	Halts workflow on first error
continue	Skips failed items, passes successful ones through
errorPort	Routes failed items to Error output port

Tips

Grok Video Gen generates videos from text prompts via the xAI API, with configurable duration and multiple video outputs per request. Orientation and dimensions are not configurable — the API takes no size parameter, so describe the framing you want in the prompt. Use this tool when a workflow needs AI-generated video content produced directly from natural language descriptions. It outputs completed video files stored as binary data on the main channel, with generation failures routed to the error output.