Grok Image Generation

Generate images using xAI Grok Aurora model

Overview

Grok Image Generation creates images from text prompts using xAI’s Grok Imagine image models. When Response Format is “Binary Data”, the generated image is decoded and attached to the output item as binary data. When it is “Image URL”, the tool returns a temporary image URL in the JSON output instead. Generates 1-4 images per request.

Category: AI
Tool Name: grok_image_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 xAI Grok Imagine image model to use for generation.
				Options: the Grok Imagine image models currently available — the dropdown tracks the model catalog, so it changes as xAI’s line-up changes.
Prompt	string	Yes	—	A text description of the desired image. Falls back to the input item’s “prompt” field when left empty. Supports expressions like {{ $json.description }}.
Options	collection	No	{}	Optional generation and output settings — add only the fields you want to override.
— Number of Images	number	No	1	Number of images to generate (1-4).
— Response Format	options	No	binaryData	How to return the generated image(s). Binary Data decodes and stores the image as binary. Image URL returns a temporary URL.
				Options: binaryData, imageUrl
— Output Binary Property	string	No	data	Name of the binary property to write the output image(s) to. Names are case-sensitive — see the upstream node’s Binary Data panel for the exact names to use.
Include Input	boolean	No	false	Whether to include the original input item fields in the output alongside the generated image.
Max Concurrency	number	No	5	Maximum number of items to process concurrently. Keep low to respect xAI rate limits.

Output Data

One output item per generated image — an input item asking for four images produces four output items, not one. The rest of the input JSON is carried over only when Include Input is on.

• imageIndex — the position of this image within the request, starting at 0.
• imageUrl — a temporary URL for the image. Present only in imageUrl mode.

In binaryData mode the image itself is attached to the output item as binary data under the name given by Output Binary Property (data by default), merged alongside any binary the input item already carried. In imageUrl mode no new binary is produced and the input item’s binary is forwarded unchanged.

Reference the result downstream by expression, e.g. {{ $json.imageUrl }}, or connect the output straight to a node that consumes binary data.

Usage Examples

• Generate an image from a text prompt using Grok Aurora
• Create multiple images from a single prompt
• Generate an image and get back a URL instead of binary data
• Create AI-generated artwork from a description

Example Configuration

Generate one image and pass it downstream as binary:

{
  "type": "grok_image_gen",
  "parameters": {
    "prompt": "A serene mountain landscape at sunrise, photorealistic"
  }
}

Generate four variations under a named binary property:

{
  "type": "grok_image_gen",
  "parameters": {
    "prompt": "{{ $json.description }}",
    "includeInput": true,
    "maxConcurrency": 2,
    "options": {
      "n": 4,
      "responseFormat": "binaryData",
      "binaryPropertyName": "artwork"
    }
  }
}

Return a temporary URL instead of binary data:

{
  "type": "grok_image_gen",
  "parameters": {
    "prompt": "A cozy coffee shop interior with warm lighting",
    "maxConcurrency": 1,
    "options": {
      "n": 1,
      "responseFormat": "imageUrl"
    }
  }
}

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 Image Generation creates images from text prompts using xAI’s Grok Imagine image models. Use it when a workflow needs AI-synthesized visuals from descriptive text and requires either a returnable URL or stored binary data for downstream processing. It outputs up to 4 images per request as either a decoded binary image written to the binary store or a direct image URL in the JSON response.