Image generation

Nano Banana 2 image

Generate an original image from a text prompt, or EDIT images you supply, using Google Nano Banana 2 at 2K resolution.

Send image_handles, image_urls or image_base64 to edit, restyle or combine up to 14 reference images; send none and it generates from the prompt alone. Editing costs exactly what generating costs and the extra references are free. Returns the URL of the generated image. Those URLs are temporary: Goro holds a run's results for 24 hours and nothing guarantees the file outlives that, so collect what you need within 24 hours.

When to use it

Use when you need an image made to order rather than found, OR when you have an image and want it changed: a hero image, an ad creative, a product mockup, an illustration, a background swapped, a product dropped into a scene, several references merged into one composition. Strongest of the cheaper image models at prompt following and at legible text inside the image. For the hardest edits and the best text, use image.nano_banana_pro. One image out per call.

Inputs

Nano Banana 2 image takes 7 fields, 1 of them required. Anything you leave out falls back to the tool's own default.

How to call it

Connect once and your agent can reach Nano Banana 2 image the same way it reaches everything else in the catalog. Add Goro as an MCP connector, or paste the setup line into an agent that reads skills.

Or plain HTTP

POST /v1/run

{
  "endpoint": "image.nano_banana",
  "input": {
    "prompt": "<prompt>",
    "resolution": "2K",
    "aspect_ratio": "1:1",
    "output_format": "png"
  }
}