Available now

Nano Banana 2 Lite: image editing

By Google

Google's Nano Banana 2 Lite creates images from a description and edits the photos you upload, in shapes from square to 8:1 and 1:8.

Model ID
Maker
Google

Input

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

Example prompt. Edit it or write your own.

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

Uploading a file needs an account. Create account

JPEG, PNG, WebP · up to 25 MB

Additional settings

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

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.

When set, enables model thinking with the given level ('minimal' or 'high') and includes thoughts in the generation. Omit to disable.

Price$0.16 / run

You sign up first. Your settings are kept.

About this model

Overview

Nano Banana 2 Lite makes one to four images per run from a written description, in 14 aspect ratios or an automatic shape chosen from your prompt. It saves as JPEG, PNG or WebP.

In the edit mode you upload one or more images and say what to change. A system prompt can hold one style across a series, and an optional thinking level lets the model reason about the prompt before it draws.

What you can build

  • Quick drafts to test an idea before a final render
  • Very wide or very tall banners and strips
  • Small edits to a photo: a new color, object or background
  • Image series that share one look through a system prompt

Prompting tips

  • Leave the aspect ratio on auto when the prompt already says portrait, landscape or banner.
  • When editing, name what stays as it is, such as the face, the text or the product.
  • Set the thinking level to high for prompts with many objects or exact placement.

What to check

Inspect lettering and subjects near the edges, especially with extreme aspect ratios.

Inputs

  • Prompt (required): The prompt for image editing.
  • System Prompt (optional): Optional system instruction that steers the model's persona and output style across the request.
  • 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.
  • Images (required): The URLs of the images to use for image-to-image generation or image editing.
  • Number of Images (optional): The number of images to generate. From 1 to 4.
  • Seed (optional): The seed for the random number generator.
  • 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.
  • Limit Generations (optional): Experimental parameter to limit the number of generations from each round of prompting to 1. Set to `True` to to disregard any instructions in the prompt regarding the number of images to generate and ignore any intermediate images generated by the model. This may affect generation quality.
  • Thinking Level (optional): When set, enables model thinking with the given level ('minimal' or 'high') and includes thoughts in the generation. Omit to disable. Options: minimal, high.

Output and limits

  • 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

  • up to, default options: $0.16 / run