Google DeepMind Launches Nano Banana 2: Pro-Level Image Generation at Flash Speed

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.