Tous les modèles
Génération d'images
Disponible maintenant

Nano Banana 2

par Google DeepMind

Nano Banana 2 by Google DeepMind brings Nano Banana Pro's quality to Flash inference speed. Generate and edit images up to 4K with subject consistency across 5 characters and 14 objects, real-world grounding via Google Search, and accurate multilingual text rendering.

Text-to-imageImage-to-imageMulti-turn editingSubject consistencyText renderingWeb-grounded generationMulti-image composition

Nano Banana 2

par Google DeepMind

Fonctionnalités clés

Ce qui distingue Nano Banana 2 des autres modèles IA.

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

Spécifications techniques

Spécifications clés et capacités en un coup d'œil.

512px – 4K

Resolution

Full range for social, web, and print

14

Aspect ratios

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

5 + 14

Reference subjects

Up to 5 characters and 14 objects for consistency

Gemini 3.1 Flash Image

Model

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

SynthID

Watermark

Built-in provenance watermark on all output

Cas d'utilisation

Comment les créateurs et les entreprises utilisent Nano Banana 2 sur Morphic.

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.

Exemples de prompts

Commencez avec ces prompts. Collez-les dans Morphic et appuyez sur générer.

Brand mascot consistency

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

Localized signage

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

Grounded landmark

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

Questions fréquemment posées

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.

Essayer Nano Banana 2
sur Morphic

Inscrivez-vous sur Morphic pour commencer à créer avec Nano Banana 2. Pas de téléchargements, pas de configuration, décrivez simplement ce que vous voulez et générez.