Google Unveils Nano Banana 2 for Advanced AI Generation
Google's latest AI model, Nano Banana 2, raises the bar for image and text generation. It excels at finding visual references, maintaining character consistency, and creating clear, legible text within images.
Key Upgrades and Availability
- Nano Banana 2 (Gemini 3.1 Flash Image) will replace Nano Banana Pro in the Gemini app. Subscribers to Google AI Pro and Ultra will retain access to the Pro version.
- The new model is being rolled out across Google's ecosystem, including Search (AI Mode and Lens), AI Studio, the Gemini API, the Google Antigravity platform, Vertex AI, and as the default model for the Flow video service.
- By tapping into Gemini's knowledge base and Google Search, the model generates highly precise images of specific items and excels at rendering and translating text.
Unprecedented Consistency and Creative Control
- Compared to its predecessor, Nano Banana 2 dramatically improves visual consistency. It can maintain the appearance of up to five characters and 14 objects, making it ideal for creating consistent visual narratives or video frames.
- The model better understands complex prompts and captures subtle creative nuances. It also provides greater user control, offering adjustable aspect ratios and resolutions ranging from 512px to 4K.
