Google has released Nano Banana 2 (Gemini 3.1 Flash Image), a major update to its image generation technology. Designed for users ranging from creative professionals to marketers and educators, this model is now available to the public through a broad rollout across Google products. Nano Banana 2 offers rapid image generation with advanced world knowledge, pulling real-time information and imagery from the web to accurately render complex subjects. It supports precise text rendering and translation, enabling global localization of content.
We’re launching Nano Banana 2, built on the latest Gemini Flash model. 🍌
— Google DeepMind (@GoogleDeepMind) February 26, 2026
It’s state-of-the-art for creating and editing images, combining Pro-level capabilities with lightning-fast speed. 🧵 pic.twitter.com/b3sHCAhrSy
Key technical improvements include:
- Maintaining subject consistency for up to five characters and 14 objects.
- Strict adherence to complex instructions.
- Production-ready visuals with resolutions from 512px to 4K, supporting various aspect ratios.
The model is now the default option in the Gemini app, Google Search (AI Mode and Lens), AI Studio, Gemini API, Google Cloud (Vertex AI), Flow, and Google Ads. This expansion brings the technology to 141 new countries and supports eight additional languages. Nano Banana 2 builds on the speed of Gemini Flash while delivering higher fidelity and more accurate results compared to its predecessors, closing the gap between quick output and image quality.
Google has also strengthened provenance features with SynthID and C2PA Content Credentials, increasing transparency around AI-generated media. As part of Google’s commitment to responsible AI, these features help users identify and understand synthetic content, supporting a wide range of creative and professional workflows.
