Google Releases Nano Banana 2: Next-Gen Image Model Combining Pro Capabilities with Lightning Speed

Google DeepMind today released Nano Banana 2 (Gemini 3.1 Flash Image), the latest generation of image generation model following last year’s viral Nano Banana sensation. This model combines the advanced features of Nano Banana Pro with the lightning speed of Gemini Flash, enabling users to achieve rapid edits and iteration while maintaining professional-grade quality.

Fusion of Speed and Intelligence

Nano Banana 2 brings Gemini Flash’s high-speed intelligence to visual generation, making rapid edits and iteration possible. It makes once-exclusive Pro features accessible to a wider audience:

Advanced World Knowledge

The model pulls from Gemini’s real-world knowledge base and is powered by real-time web search to more accurately render specific subjects. This deep understanding also helps create infographics, turn notes into diagrams, and generate data visualizations.

Precision Text Rendering and Translation

Nano Banana 2 allows generation of accurate, legible text for marketing mockups or greeting cards. Users can even translate and localize text within an image to share ideas globally.

Enhanced Creative Control

Nano Banana 2 dramatically closes the gap between speed and visual fidelity, delivering high-quality, photorealistic imagery:

Multi-Platform Rollout

Nano Banana 2 is rolling out today across Google products:

Content Provenance and Verification

Google continues deepening its provenance approach by coupling SynthID technology with C2PA Content Credentials to help identify and verify AI-generated content.

Read the full article at https://blog.google/innovation-and-ai/technology/ai/nano-banana-2/

← All articles