Google Rolls Out Nano Banana 2 Across Its Product Line

Google has released Nano Banana 2, officially named Gemini 3.1 Flash Image, an image generation and editing model that combines the capabilities of its premium Nano Banana Pro model with the speed of the Gemini Flash architecture. The model is available starting today across Google's products, including the Gemini app, Search, AI Studio, the Gemini API, Vertex AI, Flow, and Google Ads.

The release follows a rapid succession of image models from Google. The original Nano Banana, built on Gemini, became what the company describes as a viral sensation after its launch in August of last year, reshaping how users approached image generation and editing. In November, Google followed with Nano Banana Pro, which added advanced intelligence and studio-quality creative controls. Nano Banana 2 now folds the Pro tier's capabilities into a faster model.

"Now you can get the advanced world knowledge, quality and reasoning you love in Nano Banana Pro, at lightning-fast speed," Google said in its announcement.

The company frames the new model as making previously Pro-exclusive features accessible to a wider audience. Two capabilities stand out. First, Nano Banana 2 draws on Gemini's real-world knowledge base and uses real-time information and images retrieved from web search to render specific subjects more accurately. Google says this grounding also supports practical outputs such as infographics, diagrams generated from notes, and data visualizations. Second, the model handles precision text rendering, producing accurate and legible text for uses like marketing mockups and greeting cards. It can also translate and localize text within an image itself.

On the creative control side, Nano Banana 2 ships with measurable improvements over the original Nano Banana. The model maintains character resemblance for up to five characters and preserves the fidelity of up to 14 objects within a single workflow, which Google positions as useful for storyboarding and building multi-step visual narratives without characters drifting in appearance. Instruction following has been tightened as well, so the model adheres more strictly to complex prompts. For production work, users get control over aspect ratios and resolutions ranging from 512px to 4K. Google also cites a general visual fidelity upgrade: more vibrant lighting, richer textures, and sharper detail at Flash-tier speed.

The distribution strategy signals how Google intends to position the model. In the Gemini app, Nano Banana 2 replaces Nano Banana Pro across the Fast, Thinking, and Pro modes. Google AI Pro and Ultra subscribers retain access to Nano Banana Pro for specialized tasks by regenerating images through the three-dot menu. In Search, the model is available in AI Mode and Lens via the Google app and mobile and desktop browsers, expanding to 141 new countries and territories and adding eight more languages. Developers get early access through a preview in AI Studio and the Gemini API, with pricing published separately, and the model is also available in Google Antigravity. On the enterprise side, it is in preview with the Gemini API in Vertex AI on Google Cloud. In Flow, Google's filmmaking tool, Nano Banana 2 becomes the default image generation model, free for all Flow users at zero credits. Google Ads is already using it to power suggestions during campaign creation.

Google is pairing the release with a renewed push on provenance. The company couples its SynthID watermarking technology with interoperable C2PA Content Credentials, which Google says gives users "a more holistic and contextual view of not just if AI was used, but how." The company reports that SynthID verification in the Gemini app has been used over 20 million times across various languages since launching in November, helping people identify Google AI-generated images, video, and audio. C2PA verification will come to the Gemini app soon.

The release matters beyond Google's product surface. Image generation has become one of the most competitive fronts in consumer AI, and Google is consolidating a single fast model across search, advertising, developer APIs, and creative tools rather than fragmenting capabilities across tiers. The heavy provenance emphasis also reflects growing regulatory and public pressure around identifying synthetic media. With Nano Banana 2 replacing Pro in the Gemini app's default modes and expanding to 141 new markets, Google is betting that speed plus web-grounded accuracy will define the next phase of the image generation race.