Nano Banana 2.1
by Google DeepMind
Google DeepMind's new Flash image model.
Better design, cleaner edits, steadier characters.

Key features
Technical specifications
1K to 4K
1K default, 2K, and 4K output
14
From tall 1:8 to ultra-wide 8:1
Up to 14
4 characters and 10 objects
3 levels
Minimal, medium (default), high
Use cases

Infographics and explainers
Turn notes or a topic into a labeled diagram, process flow, or cutaway for lessons, reports, and social posts.

Posters and campaign art
Event posters, sale banners, and ad layouts where the headline has to read cleanly at a glance.

Product shots in new scenes
Place one product into many settings while its shape, color, and details stay true to the original.

Group shots and series
Keep a cast of up to 4 characters consistent across a campaign, a storyboard, or a run of social posts.

Localized visuals
Rework a sign, menu, or ad in another language while the layout and lettering style stay the same.

Targeted photo edits
Mask or sketch over just the part to change, a sofa, a sky, a label, and leave the rest of the photo alone.
Prompt examples



Group shot
Four friends posing on a sunny rooftop, editorial fashion shot, distinct outfits
Edit promptOverview
Nano Banana 2.1 is Google DeepMind's image generation and editing model, released on October 6, 2026 in the Gemini app, AI Mode in Search, Google AI Studio, the Gemini API, and Google Cloud. It updates Nano Banana 2 at the same Flash speed and is built on Gemini 3.6 Flash. Specs and benchmarks are in Google DeepMind's model card and the Gemini API model page.
What Nano Banana 2.1 does better
The largest gains are in design and editing. Infographics get tidier layouts and more accurate facts, masked and sketched edits land where you mark them, and a cast of up to 4 characters stays recognizable across a scene. A thinking step plans the image first, and you can turn it up for dense, detailed work.
Nano Banana 2.1 on Morphic
Nano Banana 2.1 is coming to Morphic. Until then, Nano Banana 2, Nano Banana Pro, and Nano Banana 2 Lite are live for generation and editing, and you can run the same prompt across models side by side on one Canvas. The examples on this page were made with Nano Banana 2.
Simple pricing
Get started for free today, with the option to upgrade or cancel anytime.
Basic
2400 monthly credits
1 user only
All models
Workflows
Standard
3625 monthly credits
1 user only
All models
Workflows
Pro
6350 shared monthly credits
1 user
All models
Workflows
Max
24650 shared monthly credits
1 user
All models
Workflows
Enterprise
For higher limits
Custom
pricing and billing terms

Free
For playing around
$0
forever free
FAQs
Vidu Q4
Shengshu Technology
Shengshu's latest video model. Up to 12 reference images and 3 voices held consistent across one clip, with native audio from 540p to 4K.
Flux 3 Image
Black Forest Labs
Black Forest Labs' control-first image model. Place every element, edit one box at a time.
Ideogram 4.5
Ideogram
Ideogram's precision edit model. Stack edit on edit, with no drift or artifacts.
Eleven v4
ElevenLabs
ElevenLabs' most expressive voice model. Audio tags, 90+ languages, and a faster Turbo tier.