Google DeepMind has launched Nano Banana 2, a new image generation model that combines the speed of Gemini Flash with the capabilities of Nano Banana Pro.
The model, also referred to as Gemini 3.1 Flash Image, is rolling out across Google products, including the Gemini app, Search, Google Cloud, AI Studio, Flow and Google Ads.
The company said Nano Banana 2 delivers advanced world knowledge, subject consistency, instruction following and production-ready outputs at faster speeds.
“Today, we’re bringing the best of both worlds to users across Google,” the company said in a blog post. “Now you can get the advanced world knowledge, quality and reasoning you love in Nano Banana Pro, at lightning-fast speed.”
According to Google, Nano Banana 2 integrates Gemini’s real-world knowledge base and draws on real-time information and images from web search to improve subject accuracy. The company said this enables users to generate infographics, convert notes into diagrams and create data visualisations with improved grounding.
The model also supports precise text rendering and in-image translation. Google said users can generate legible marketing mockups or greeting cards and localise text within images for different markets.
Nano Banana 2 maintains character resemblance for up to five characters and preserves fidelity for up to 14 objects in a single workflow. The company said this allows users to storyboard and build visual narratives without altering inputs.
Google added that the model adheres more strictly to complex instructions and supports aspect ratios and resolutions ranging from 512 pixels to 4K.
“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,” the company said.
In the Gemini app, Nano Banana 2 will replace Nano Banana Pro across Fast, Thinking and Pro modes, although Google AI Pro and Ultra subscribers will retain access to Nano Banana Pro via regeneration options.
The model is also available in AI Mode and Lens in Search across mobile and desktop, expanding to 141 new countries and territories and eight additional languages.
Nano Banana 2 is available in preview through AI Studio and the Gemini API, including in Vertex AI on Google Cloud, and becomes the default image generation model in Flow. It also powers image suggestions in Google Ads during campaign creation.
Nano Banana first launched in August 2025, followed by Nano Banana Pro in November. With Nano Banana 2, Google is consolidating its image generation capabilities into a single model focused on speed, instruction accuracy and broader distribution across its ecosystem.
ALSO READ: Red Hat & NVIDIA Launch AI Factory For Enterprise-Scale Deployment
