Image generation
Available now

Nano Banana 2

by Google DeepMind

Google DeepMind's Flash‑speed image model.
Up to 4K, subject consistency across 5 characters and 14 objects, with real‑world grounding.

Nano Banana 2

by Google DeepMind

Key features

Same fox mascot in three poses, flat illustration, consistent color paletteTry now

Technical specifications

512px – 4K

Full range for social, web, and print

14

From 1:1 and 16:9 to ultra-wide 8:1 and 21:9

5 + 14

Up to 5 characters and 14 objects for consistency

Gemini 3.1 Flash Image

API model: gemini-3.1-flash-image-preview

SynthID

Built-in provenance watermark on all output

Use cases

Character-consistent series

Build out brand mascots, story characters, or campaign talent across many images with the same identity preserved.

Localized marketing visuals

Generate the same scene with text translated and adapted across languages, useful for international campaign rollouts.

Real-world grounded imagery

Depict real landmarks, products, and current events accurately through optional web grounding during generation.

Iterative design reviews

Flash-speed generation suits design teams that want fast turnaround on rounds of revisions and exploratory variations.

Product mockups with accurate text

Packaging, signage, and label work where brand names and copy must render correctly and legibly.

Multi-image composition

Combine reference images of products, people, and scenes into a single composition with consistent lighting and style.

Prompt examples

Brand mascot consistency

Same fox mascot in three poses: waving, smiling, jumping, flat illustration

Edit prompt

Localized signage

Tokyo café sign reading 'Open' in Japanese, soft morning light

Edit prompt

Grounded landmark

Eiffel Tower at golden hour, postcard style, vivid pastel sky

Edit prompt

Overview

Nano Banana 2 is Google DeepMind's image model based on Gemini 3.1 Flash Image, released February 2026. It brings the precision features of Nano Banana Pro (subject consistency across up to 5 characters and 14 objects, accurate text rendering, real-time web grounding through Google Search, and resolutions up to 4K) to Flash inference speed. The result is fast enough for iteration loops and high-volume production while keeping the quality bar that made Nano Banana Pro a reference point for image generation.

Simple pricing

Get started for free today, with the option to upgrade or cancel anytime.

Basic

$9/ month
billed as $0 per year

1100 monthly credits

1 user only

All models

Workflows

Standard

$24/ month
billed as $0 per year

3625 monthly credits

1 user only

All models

Workflows

Pro

$45/ month
billed as $0 per year

6350 shared monthly credits

1 user

+ up to 4 more at extra cost

All models

Workflows

Pro Max

$170/ month
billed as $0 per year

24650 shared monthly credits

1 user

+ up to 9 more at extra cost

All models

Workflows

Enterprise

For higher limits

Custom

pricing and billing terms

High-volume credits
Custom seat limits
All models
Workflows
Pricing Gradient

Free

For playing around

$0

forever free

Up to 20 credits
1 user only
Limited models
Workflows
Compare plan details

FAQs

What is Nano Banana 2?
Nano Banana 2 is Google DeepMind's image model based on Gemini 3.1 Flash Image, released February 2026. It brings Nano Banana Pro's quality features to Flash inference speed.
How is Nano Banana 2 different from Nano Banana Pro?
Nano Banana Pro (Gemini 3 Pro Image) prioritizes maximum quality and factual depth. Nano Banana 2 keeps subject consistency, text rendering, and grounding, but runs at Flash speed for faster iteration.
What resolutions does Nano Banana 2 support?
Resolutions from 512px up to 4K across 14 aspect ratios including 1:1, 16:9, 9:16, 21:9, 4:5, and ultra-wide 8:1 and 1:8.
Can Nano Banana 2 keep the same character across multiple images?
Yes. It supports subject consistency for up to 5 characters and up to 14 objects, suited for storyboards, brand mascots, and character-driven series.
When should I use Nano Banana 2 vs ChatGPT Images 2.0 or Flux?
Use Nano Banana 2 for fast iteration with real-world grounding and subject consistency. Use ChatGPT Images 2.0 for native reasoning and text-heavy compositions. Use Flux for style versatility and photorealistic range.
How do I use Nano Banana 2 on Morphic?
Open Copilot, describe what you want, and select Nano Banana 2. Its Flash-speed inference makes it ideal for rapid iteration, try multiple directions, pick the strongest, and either keep going on Nano Banana 2 or hand the winning prompt to Nano Banana Pro for the final.

More about Nano Banana 2

Guides, prompts, and comparisons for Nano Banana 2.

Nano Banana 2 vs ChatGPT Images 2.0: which to pick for what

Match the AI image model to the task. See where Nano Banana 2 shines, where ChatGPT Images 2.0 leads, and which to pick for your specific use case.

Nano Banana 2 vs ChatGPT Images 2.0: Side-by-Side Examples

Eight side-by-side examples from Nano Banana 2 and ChatGPT Images 2.0 using the same prompts. See the head-to-head outputs across portraits, text, layouts, and more.

Other models

Explore the rest of the Morphic model catalog.

See all models →

ChatGPT Images 2.5

OpenAI

OpenAI's image model, released September 2026. Sharper detail, precise edits, faster.

Lyria 3.5

Google DeepMind

Google's best-sounding music model. Full songs with structure, vocals, and lyrics.

MiniMax H3 Max Turbo

fal.ai

The fast tier of fal's post-trained H3. Twice the speed, nearly the same look.

Inworld TTS 2

Inworld

Ninety-five voices, 100+ languages. Speech that starts in under a second.