Nano Banana 2 Lite

Nano banana lite is the efficiency-focused model in the image generation family. Sub-2 second latency with cost-effective generation and editing, fast multi-turn local edits, and 14 supported aspect ratios.

Input

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

The text prompt to generate an image from.

Tips and requirements

The aspect ratio of the generated image. Supports extreme ratios: 4:1, 1:4, 8:1, 1:8. Use "auto" to let the model decide based on the prompt.

The number of images to generate.

Additional settings
Tips and requirements

Optional system instruction that steers the model's persona and output style across the request. Leave blank to omit; when provided, it is sent as the system instruction to Gemini (or as a system message on OpenAI-compatible providers).

The seed for the random number generator.

The format of the generated image.

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

Tips and requirements

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.

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.

API code for this input

Complete the required fields and fix input errors to see API code.

How to use Nano Banana 2 Lite

Getting started

Explore a composition before adapting it to a banner or portrait layout.

Review your result

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

Inputs and settings

Send prompt and choose aspect_ratio; 4:1, 1:4, 8:1 and 1:8 are available. num_images allows 1–4 outputs.

system_prompt can hold shared style instructions. To change an existing image, select the separate edit mode and supply image_urls.