Available now

Nano Banana 2: image editing

By Google

Google's Nano Banana 2 makes and edits images, from small 0.5K drafts up to 4K, in shapes from square to extra wide.

Model ID
Maker
Google

Input

Fields marked * are required. Review the price before generating.

Example prompt. Edit it or write your own.

Uploading a file needs an account. Create account

JPEG, PNG, WebP · up to 25 MB

Supports extreme ratios: 4:1, 1:4, 8:1, 1:8.

Additional settings

The seed for the random number generator.

The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict.

Optional system instruction that steers the model's persona and output style across the request.

Estimated total · 1K$0.13

You sign up first. Your settings are kept.

About this model

Overview

Nano Banana 2 creates one to four images from a written brief, at 0.5K, 1K, 2K or 4K, in shapes from square to extreme formats such as 8:1 and 1:8.

The edit mode takes one or more of your images and a written instruction: change a detail, restyle the picture or combine several images into one.

What you can build

  • Small drafts to test many ideas before choosing one
  • Social posts in square, portrait and story formats
  • Restyled versions of an existing photo
  • Simple composites from a few product photos

Prompting tips

  • Test ideas at 0.5K, then rerun the one you like at a higher resolution with the same seed.
  • Keep the seed fixed when you compare small prompt changes.
  • Say what the image is for, for example a banner with empty space on the left for text.

What to check

Inspect small lettering and object placement at the final output size.

Inputs

  • Prompt (required): The prompt for image editing.
  • Images (required): The URLs of the images to use for image-to-image generation or image editing.
  • Thinking Level (optional): Controls thinking effort ('minimal' or 'high') and requests thought summaries. Leave it empty for the default ('minimal'); thinking cannot be disabled. Options: minimal.
  • Number of Images (optional): The number of images to generate. From 1 to 4.
  • Seed (optional): The seed for the random number generator.
  • Aspect Ratio (optional): The aspect ratio of the generated image. Supports extreme ratios: 4:1, 1:4, 8:1, 1:8. Options: auto, 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16, 4:1, 1:4, 8:1, 1:8.
  • Output Format (optional): The format of the generated image. Options: jpeg, png, webp.
  • Safety Tolerance (optional): The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict. Options: 1, 2, 3, 4, 5, 6.
  • System Prompt (optional): Optional system instruction that steers the model's persona and output style across the request.
  • Resolution (optional): The resolution of the image to generate. Options: 0.5K, 1K, 2K, 4K.

Output and limits

  • Resolutions: 0.5K, 1K, 2K, 4K.
  • Aspect ratios: auto, 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16, 4:1, 1:4, 8:1, 1:8.
  • File formats: JPEG, PNG, WEBP.
  • Up to 4 images per run.
  • Small or dense text in the image can come out misspelled.
  • Hands, crowds and complex poses can show artifacts; generate a few variations and pick the best.
  • Some prompts or outputs can be refused by safety checks.

Price guide

  • 0.5K: $0.10 / image
  • 1K: $0.13 / image
  • 2K: $0.20 / image
  • 4K: $0.26 / image