Google DeepMind 发布 Nano Banana 2（Gemini 3.1 Flash Image）图像模型

Feb 26, 2026

Our latest image generation model offers advanced world knowledge, production-ready specs, subject consistency and more, all at Flash speed.

Naina Raisinghani

Product Manager, Google DeepMind

Nano Banana 2 text with AI generated images around it

Listen to article

[[duration]] minutes

This content is generated by Google AI. Generative AI is experimental

In August of last year, our Gemini Image model, Nano Banana, became a viral sensation, redefining image generation and editing. Then in November, we released Nano Banana Pro, offering users advanced intelligence and studio-quality creative control. Today, we’re bringing the best of both worlds to users across Google.

Introducing Nano Banana 2 (Gemini 3.1 Flash Image), our latest state-of-the-art image model. Now you can get the advanced world knowledge, quality and reasoning you love in Nano Banana Pro, at lightning-fast speed.

Intelligence and visual quality at Flash speed

Nano Banana 2 brings the high-speed intelligence of Gemini Flash to visual generation, making rapid edits and iteration possible. It makes once-exclusive Pro features accessible to a wider audience, including:

Advanced world knowledge: 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. This deep understanding also helps you create infographics, turn notes into diagrams and generate data visualizations.
Precision text rendering and translation: Nano Banana 2 allows you to generate accurate, legible text for marketing mockups or greeting cards. You can even translate and localize text within an image to share your ideas globally.

High-quality flat lay photography of a DIY infographic explaining the water cycle on a clean, light gray textured background with hand-drawn black arrows to guide the viewer through the process

A three-panel comic-style infographic in 16:9 aspect ratio comparing Cumulus, Stratus, and Cirrus clouds, each shown in a dramatic sky with a bold label

A 16:9 aspect ratio image of Museum Clos Lucé rendered in the style of bright-colored Synthetic Cubism without any text

2 images on a white background: First, A cinematic close-up of an intricately illustrated sign made of recycled material featuring local birds and flowers and text that reads "Native Wildlife: Please Observe from a Distance" against a soft blur of green foliage. Second, a version of the "Native Wildlife" sign localized for an Indian setting, with all text translated into Hindi

Read the prompts: Water Cycle ¹ , Cloud Infographic ² , Cubism ³ , Wildlife Sign ⁴

Enhanced creative control

Nano Banana 2 also dramatically closes the gap between speed and visual fidelity, delivering high-quality, photorealistic imagery. Here’s what our newest model offers and has improved on from the original Nano Banana:

Subject consistency: Maintain character resemblance of up to five characters and the fidelity of up to 14 objects in a single workflow, allowing you to storyboard and build narratives without altering the appearance of your inputs.
Precise instruction following: With enhanced instruction following, the model adheres more strictly to your complex requests, capturing the specific nuances of your idea so the image you get is the image you asked for.
Production-ready specs: Make attention grabbing assets with full control of various aspect ratios and resolutions from 512px to 4K, ensuring your visuals stay sharp whether they are for a vertical social post or a wide-screen backdrop.
Visual fidelity upgrade: Nano Banana 2 delivers vibrant lighting, richer textures and sharper details, maintaining high-quality aesthetics at the speed expected from Flash.

A silly and joyful image showing 14 consistent characters and items having fun together in a farm setting

A 16:9 story sequence showing three fluffy characters building a treehouse, with various expressions and angles across multiple panels

A moody and atmospheric high-angle aerial view of a misty valley with lush green hills, a winding road, and a dark blue-grey body of water reflecting an overcast sky

A vibrant pop-art style image of an individual in a striking suit with blue swirling patterns and pink circles, wearing heart-shaped sunglasses, posed against a solid cerulean blue background, in different aspect ratios

Read the prompts: Farm ⁵ , Treehouse ⁶ , Valley ⁷ , Portrait ⁸

Try Nano Banana 2 today

Whatever your needs, we now offer the perfect tool for every workflow: Nano Banana Pro for high-fidelity tasks requiring maximum factual accuracy, or Nano Banana 2 for rapid generation, precise instruction following and integrated image-search grounding.

Nano Banana 2 is rolling out today across Google products, including:

Gemini app: Nano Banana 2 will replace Nano Banana Pro across the Fast, Thinking and Pro models. Google AI Pro and Ultra subscribers will keep access to Nano Banana Pro for specialized tasks by regenerating images via the three-dot menu.
Search: In AI Mode and Lens, through the Google app as well as mobile and desktop browsers. View availability here, including 141 new countries and territories and eight additional languages.
AI Studio + API: Available in preview in AI Studio and Gemini API. Pricing here. Also available in Google Antigravity.
Google Cloud: Available in preview with the Gemini API in Vertex AI.
Flow: Nano Banana 2 is the new default image generation model in Flow, available to all Flow users for zero credits.
Google Ads: Nano Banana 2 is available now, powering suggestions while creating campaigns in Google Ads.

A user interface for the Gemini app template feature labeled, "Pick a style for your image." It shows a grid of 12 preview tiles with different artistic styles like "Monochrome," "Gothic clay," and "Steampunk," above a text prompt box that says "Describe your image."

A side-by-side comparison of two graphite pencil sketches showing different interpretations of a pufferfish nest: one a less accurate, textured, shell-lined crater and the other a more accurate geometric, scientific diagram in a field notebook with handwritten annotations.

A four-panel collage featuring a whimsical kangaroo on vacation: steering a small blue boat at sea, sipping espresso at a Parisian cafe, lounging in a white bathrobe on a bed, and jumping in a colorful bouncy castle.

Read the prompts: AI Mode in Search ⁹ , Flow ¹⁰

Robust provenance: marking and verification

As generative media evolves, so must the tools we use to identify and understand it. We continue to deepen our provenance approach, by coupling our state-of-the-art SynthID technology with interoperable C2PA Content Credentials, we provide users with a more holistic and contextual view of not just if AI was used, but how.

Our provenance tools are already making an impact. Since its launch in November, our SynthID verification feature in Gemini app has been used over 20 million times across various languages, helping people identify Google AI-generated images, video and audio. We’ll soon be bringing C2PA verification to the Gemini app, too.

Get the latest news from Google in your inbox

Your information will be used in accordance with Google's privacy policy. You may opt out at any time.