Pro-level image generation and editing at Flash-level speed. Advanced world knowledge, 4K resolution, subject consistency, and precision text rendering.
Launched February 26, 2026 — Gemini 3.1 Flash Image by Google DeepMind
Combines the advanced world knowledge, quality, and reasoning of Nano Banana Pro with the lightning-fast speed of Flash. Get Pro-level capabilities without the wait.
Rapid generation and iteration make it possible to quickly explore ideas and refine your vision. Dramatically closes the gap between speed and visual fidelity.
Makes once-exclusive Pro features accessible to a wider audience. Advanced world knowledge, precision text rendering, and subject consistency at your fingertips.
Real outputs generated with this model — every caption is the exact prompt used.
Gold-foil 'Thank You' letterpress greeting card on cream cotton paper, premium overhead flat-lay.
Artisan bakery storefront with a bilingual French and Chinese hand-painted sign, golden morning light.
Authentic wood-fired Neapolitan margherita pizza with leopard-spotted crust, overhead food photography.
Flat-design Earth cross-section infographic with crisp labeled layers in a minimalist vector style.
Faceted glass perfume bottle with amber liquid on polished marble, dramatic side-lit 4K studio shot.
Three-panel astronaut storyboard keeping one character perfectly consistent across every frame.
Write your own prompt and generate high-resolution images with Nano Banana 2. Start free — no credit card required.
Try Nano Banana 2Nano Banana 2 (Gemini 3.1 Flash Image), developed by Google DeepMind and launched on February 26, 2026, represents the latest state-of-the-art image generation model. It brings the best of both worlds to users: the advanced world knowledge, quality, and reasoning of Nano Banana Pro combined with the lightning-fast speed of Nano Banana. This breakthrough model makes rapid edits and iteration possible while maintaining Pro-level quality.
The model pulls from Gemini's real-world knowledge base and is powered by real-time information and images from web search to more accurately render specific subjects. It dramatically closes the gap between speed and visual fidelity, delivering high-quality, photorealistic imagery with production-ready specs from 512px to 4K resolution. Nano Banana 2 maintains character resemblance of up to 5 characters and the fidelity of up to 14 objects in a single workflow, allowing users to storyboard and build narratives without altering the appearance of their inputs. All images are embedded with SynthID, Google's imperceptible watermark, and support C2PA Content Credentials for robust provenance.
Pulls from Gemini's real-world knowledge base and real-time web search to accurately render specific subjects. Create infographics, turn notes into diagrams, and generate data visualizations with deep understanding of the world.
Generate accurate, legible text for marketing mockups, greeting cards, and posters. Translate and localize text within images to share your ideas globally. Play with fonts, styles, and sizes with precision.
Maintain character resemblance of up to 5 characters and the fidelity of up to 14 objects in a single workflow. Storyboard and build narratives without altering the appearance of your inputs.
Enhanced instruction following adheres more strictly to your complex requests, capturing the specific nuances of your idea. The image you get is the image you asked for.
Full control of various aspect ratios and resolutions from 512px to 4K. Create attention-grabbing assets that stay sharp whether for vertical social posts or wide-screen backdrops.
Delivers vibrant lighting, richer textures, and sharper details. Maintains high-quality aesthetics at the speed expected from Flash, with photorealistic imagery that rivals Pro.
Flash-level speed enables rapid edits and iteration. Quickly explore ideas and refine your vision without waiting. Partners report 74-76% latency reduction, making workflows 4x faster.
Deep understanding helps create infographics, turn notes into diagrams, and generate data visualizations. Perfect for educational content, presentations, and marketing materials.
All images embedded with SynthID, Google's imperceptible watermark. Supports C2PA Content Credentials for robust provenance. Over 20 million verifications since launch.
| Type | AI Image Generation & Editing |
|---|---|
| Model | Gemini 3.1 Flash Image |
| Developer | Google DeepMind |
| Release | Feb 26, 2026 |
| Status | State-of-the-art |
| Resolution | 512px to 4K |
|---|---|
| Aspect Ratios | Multiple (vertical, horizontal, square) |
| Quality | Photorealistic, high-fidelity |
| Lighting | Vibrant, professional |
| Details | Richer textures, sharper |
| Characters | Up to 5 characters |
|---|---|
| Objects | Up to 14 objects |
| Consistency | Character resemblance maintained |
| Storyboarding | Build narratives |
| Workflow | Single workflow support |
| Knowledge Base | Gemini real-world knowledge |
|---|---|
| Web Search | Real-time information & images |
| Infographics | Create & visualize data |
| Diagrams | Turn notes into diagrams |
| Accuracy | Specific subject rendering |
| Text Rendering | Accurate, legible |
|---|---|
| Translation | Multilingual support |
| Localization | Text within images |
| Fonts | Multiple styles & sizes |
| Use Cases | Cards, mockups, posters |
| Watermark | SynthID (imperceptible) |
|---|---|
| Credentials | C2PA Content Credentials |
| Verification | 20M+ uses |
| Safety | Content filtering |
| Transparency | AI identification |
Create marketing mockups, greeting cards, and promotional materials with precision text rendering. Generate attention-grabbing assets with full control over aspect ratios and resolutions from 512px to 4K.
Turn notes into diagrams and create data visualizations with advanced world knowledge. Perfect for educational content, presentations, and explaining complex concepts visually.
Maintain character resemblance of up to 5 characters and 14 objects to build narratives without altering appearances. Perfect for comic creators, animators, and content creators.
Create stunning visuals for social posts with production-ready specs. Vertical posts, horizontal banners, or square images - all stay sharp and professional at any resolution.
Generate 4K production-ready assets for wide-screen backdrops, presentations, and professional projects. Vibrant lighting, richer textures, and sharper details at Flash speed.
Translate and localize text within images to share ideas globally. Create multilingual marketing materials, greeting cards, and posters with precision text rendering.
Not every generated image will be perfect. The model can still struggle with small faces, accurate spelling, and fine details in images. Complex text or intricate facial features may require iteration.
The model's real-world knowledge is extensive but not infallible. When generating infographics, annotating diagrams, or representing complex data, it may misinterpret information. Always verify data-driven outputs.
Capable of generating and translating text in many languages, but may struggle with grammar, spelling, cultural nuances, or idiomatic phrases. Review translations for accuracy.
Advanced features like masked editing, major lighting changes (day to night), or blending multiple images may sometimes produce unnatural results, visual artifacts, or disjointed scenes.
The model excels at character consistency but may not always get it right. Google is working to make this consistency even more reliable across complex workflows.
Don't rely on the model for medical, legal, financial, or other professional advice. Any content regarding those topics is provided for informational purposes only.
Experience Pro-level image generation at Flash-level speed. Advanced world knowledge, 4K resolution, subject consistency, and precision text rendering.
Try Nano Banana 2 now