Nano Banana is the nickname for Gemini's built-in image models, which create and edit pictures from text, images or a mix of both.
In plain words
The name began as the nickname for Gemini 2.5 Flash Image, released in August 2025. It is now what Google calls Gemini's native image generation. You can describe a picture, upload photos to combine, or ask for a small change, and refine the result over several turns of conversation. It can draw on Gemini's knowledge of the world when making or editing a picture. In September 2026 the versions on offer are Nano Banana 2, 2 Lite and Pro. Every image carries a SynthID watermark.
A quick example
Imagine uploading a photo of your living room and asking to change the sofa to dark green. You then ask for evening light, and the model edits the same picture again while leaving the rest untouched.
Where you'll meet it
- Google AI Studio and the Gemini API.
- Editing photos with plain-language instructions.
Related
Sources
- DocsIntroducing Gemini 2.5 Flash Image, Google Developers Blog · read 29 Sept 2026
- DocsNano Banana image generation, Gemini API docs · read 2 Nov 2026
- DocsGemini models, Gemini API docs · read 2 Nov 2026
Checked by WhatIsAI against the sources above · 2 Nov 2026. Spotted an error? Report it.