Google DeepMind Launches Nano Banana 2: Pro-Level Image Generation at Flash Speed
Original: Google DeepMind Launches Nano Banana 2: Pro-Level Image Generation at Flash Speed View original →
Nano Banana 2 Launch
Google DeepMind announced on February 26, 2026 via X: "We're launching Nano Banana 2, built on the latest Gemini Flash model. It's state-of-the-art for creating and editing images, combining Pro-level capabilities with lightning-fast speed."
Key Capabilities
Nano Banana 2 (officially Gemini 3.1 Flash Image) introduces several advanced features. Web search integration enables generating enhanced visuals using real-life references. Text rendering has been significantly improved with the same precision as the artwork itself, supporting in-image localization across multiple languages. Subject Consistency allows maintaining character resemblance for up to five characters and preserving fidelity of up to 14 objects within a workflow.
Top Benchmark Performance at Half the Price
Within hours of launch, independent benchmarks placed Nano Banana 2 at #1 in Text-to-Image in the Artificial Analysis Image Arena — a blind human evaluation leaderboard — at roughly half the API price of its predecessor, Nano Banana Pro.
Wide Deployment Across Google Products
The model became the default image generation engine across the Gemini app, Google Search's AI Mode, Google Lens, Google Ads, and the AI filmmaking tool Flow, now available in 141 countries. All images are automatically embedded with SynthID, Google DeepMind's invisible digital watermark, persisting through cropping, compression, and filtering.
Related Articles
Google DeepMind’s new audio model translates speech across more than 70 languages while preserving tone, pace, and pitch. The rollout spans Google Translate, Google AI Studio, the Gemini Live API, and Google Meet previews.
Google DeepMind says a Sierra Leone classroom trial shifted Gemini use toward learning behavior: queries about how to tackle problems rose from 68% to 90%. The eight-week RCT covered 1,763 students across 12 schools.
Google DeepMind has unveiled an experimental project to redesign the mouse cursor with AI — the first major rethinking of the pointer in over 50 years. Powered by Gemini, the AI-enabled pointer understands screen context and acts on voice and gesture commands.