Maia RouterInstall

Summary

Generate one or more images based on a text prompt using a specified AI image model and optional parameters like aspect ratio, size, and quality.

Inputs

• Model (required) — Select the AI image model to use (GPT Image 1, Gemini Nano Banana, or Gemini Nano Banana Pro).
• Prompt (required) — Provide the text prompt describing the desired image to be generated.
• Aspect Ratio — Choose the image aspect ratio when using Gemini models (options include 1:1, 9:16, 16:9, 3:4, 4:3).
• N (Number of Images) — Specify how many images to generate, applicable only for GPT Image 1 model (1 to 10).
• Size — Set the resolution size for generated images when using GPT Image 1 (e.g., 1024x1024).
• Quality — Set image generation quality for GPT Image 1 (Auto, High, Medium, Low).

Output shape

An array of generated images per input item.

The output will contain the generated image data as JSON for each execution input item. If multiple images are requested (N) with GPT Image 1 model, the output includes all generated images accordingly.

Examples

Example 1: Generate a single square image with GPT Image 1 using a text prompt.

Set Model to "GPT Image 1", provide the Prompt, and optionally set Size and Quality.

Example 2: Generate multiple images with GPT Image 1.

Set Model to "GPT Image 1", provide Prompt, set N to desired number of images (1-10).

Example 3: Generate an image with Gemini Nano Banana Pro specifying aspect ratio.

Set Model to "Gemini Nano Banana Pro", provide Prompt, and select Aspect Ratio from the available options.