Gemini Image Generation

Generate images using Gemini native image generation

Overview

Gemini Image Generation calls the Gemini generateContent API with an image response modality, so the picture is produced natively inside a Gemini model rather than by a separate image service. The model returns inline image data, which is decoded and written to a binary property on the output item; any text the model returns alongside it is collected into a response field. Authentication is via a Google AI API key.

Category: AI
Tool Name: gemini_image_gen
Version: 1

Appearance: Icon: gemini | Color: #ffffff

Node Type

Action (Binary) — handles file/binary data operations

Input / Output

Direction	Port(s)
Input	Input
Output	Output, Error

Credentials

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

Parameters

Parameter	Type	Required	Default	Description
Model	options	No	—	The Gemini image model — the Nano Banana family, which accepts the same generateContent + responseModalities request shape. The dropdown lists the models currently available for this node; leave it unset to use the default.
Prompt	string	Yes	—	A text description of the desired image. Gemini will generate an image (and optionally text) based on this prompt. Supports expressions like {{ $json.description }}.
Options	collection	No	{}	Optional output settings.
— Output Binary Property	string	No	data	Name of the binary property to write the output image to. Names are case-sensitive — see the upstream node’s Binary Data panel for the exact names to use.
— Response Field Name	string	No	response	JSON field name where the text response from the model will be stored.
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 Google AI rate limits.

Output Data

One output item per input item. The generated image is written to the binary property named by Output Binary Property (default data); if the model returns more than one image, the extras are written alongside it under the same name with an index suffix — data_1, data_2, and so on. Binary data arriving from upstream is preserved.

The output item’s JSON contains only the fields below. The input item’s JSON is merged in only when Include Input is on:

Field	Description
response	Any text the model returned alongside the image. Renamed by Response Field Name.
model	The model that produced the image.
imageCount	How many images were returned — 0 when the model produced none.
finishReason	Why generation stopped, when the model reports one.
promptFeedback	Prompt-level feedback (for example a block reason), when the model reports it.
usage	Token usage metadata, when the model reports it.
partTypes	Present only when no image came back — the shapes the model returned instead, which explains an empty result.

Reference the result downstream by expression, e.g. {{ $json.imageCount }}, and the image itself through the binary property name you configured.

Usage Examples

• Generate an image from a text prompt using Gemini
• Create an image with accompanying text description
• Draw a watercolor painting from a description
• Generate AI artwork using Gemini multimodal capabilities

Example Configuration

Generate a single image with the defaults:

{
  "type": "gemini_image_gen",
  "parameters": {
    "prompt": "A photorealistic golden retriever puppy playing in autumn leaves"
  }
}

Build the prompt from an upstream field and keep the source data on the item:

{
  "type": "gemini_image_gen",
  "parameters": {
    "prompt": "{{ $json.description }}",
    "includeInput": true,
    "maxConcurrency": 3,
    "options": {
      "binaryPropertyName": "generatedImage",
      "responseFieldName": "modelResponse"
    }
  }
}

Batch thumbnails one at a time to stay inside rate limits:

{
  "type": "gemini_image_gen",
  "parameters": {
    "prompt": "{{ $json.thumbnailPrompt }}",
    "includeInput": true,
    "maxConcurrency": 1,
    "options": {
      "binaryPropertyName": "thumbnail",
      "responseFieldName": "caption"
    }
  }
}

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

Gemini Image Generation calls the Gemini generateContent API with multimodal response modalities to produce images natively within Gemini models. Use this tool when you need AI-generated visuals alongside explanatory text in a single model call, authenticated via a Google AI API key. It outputs a response field containing collected text parts and decoded inline image data (base64-encoded PNG or JPEG) stored in the binary store, with errors routed to a dedicated error output.