Google DeepMind is rolling out Nano Banana 2 (Gemini 3.1 Flash Image), its latest image generation model, combining the intelligence and production controls of Nano Banana Pro with the rapid performance of Gemini Flash.
What’s new. Nano Banana 2 introduces:
Advanced world knowledge: Powered by Gemini’s real-time web grounding to better render specific subjects and generate infographics or data visualizations.
Precision text rendering and translation: Cleaner, legible text inside images — including localization.
Stronger instruction adherence: Improved handling of complex, multi-layered prompts.
Subject consistency: Maintains up to five characters and 14 objects within a single workflow.
Production-ready outputs: Supports aspect ratios and resolutions from 512px to 4K.
Enhanced visual fidelity: Sharper detail, richer textures and more dynamic lighting — at Flash speed.
Why we care. Nano Banana 2 makes high-quality, production-ready image generation faster and more scalable — reducing the time and cost of creative development. With improved text rendering, subject consistency, and 4K-ready outputs, brands can generate campaign assets, localized variations, and social formats in minutes instead of days.
Integrated directly into Google Ads and Gemini, it also tightens the loop between creative production and campaign execution, accelerating testing and iteration.
The rollout. Nano Banana 2 is launching across Google’s ecosystem, including Google Ads, Gemini app, Search AI Mode and Lens, and more.
Between the lines. Google is standardizing high-end image generation into its faster tier, signaling a broader shift: premium creative control is becoming baseline — not a paid upgrade.
The bottom line. With Nano Banana 2, Google is betting that creators want fewer trade-offs — faster generation, stronger reasoning and production-ready visuals in one default model.