TL;DR
Google has launched Nano Banana 2 (Gemini 3.1 Flash Image), a new image generation model that combines the quality of its Pro tier with the speed of Flash. The model is rolling out across the Gemini app, Google Search, Ads, Cloud, and the Flow creative tool.
What Nano Banana 2 offers
The model builds on last year’s viral Nano Banana release, bringing several capabilities previously restricted to the slower Pro version. These include advanced world knowledge drawn from web search for accurate subject rendering, precision text rendering and translation within images, and the ability to generate infographics and data visualisations.
On the creative side, Nano Banana 2 maintains character resemblance across up to five characters and 14 objects in a single workflow, enabling consistent storyboarding. It supports resolutions from 512px to 4K across various aspect ratios, and delivers what Google describes as improved lighting, textures, and detail fidelity.
Where it’s available
The rollout is broad: Nano Banana 2 replaces Nano Banana Pro as the default in the Gemini app’s Fast, Thinking, and Pro modes. Google AI Pro and Ultra subscribers retain access to the full Pro model through a regeneration menu. The model is also available in Google Search AI Mode and Lens across 141 new countries, in AI Studio and the Gemini API, in Vertex AI on Google Cloud, and as the default in Flow (Google’s creative tool) at zero credit cost.
Google is also expanding its provenance tooling. Since launching in November, the SynthID verification feature in the Gemini app has been used over 20 million times. C2PA Content Credentials verification is planned for the app as well.
Looking forward
The release signals Google’s push to make high-quality image generation a default capability across its product ecosystem rather than a premium add-on. For businesses using Google Ads or Cloud, the upgrade is automatic — though competitors will be watching whether the quality gap with dedicated image generation platforms narrows as a result.