Google launches new image generation model Nano Banana 2: what’s new?
Google has introduced an upgraded image generation model Nano Banana 2 (Gemini 3.1 Flash Image), which has already begun integrating into the company’s services. This innovation combines the advanced capabilities of the Pro version with high processing speed, making it attractive to a wide range of users.
Nano Banana 2 leverages the capabilities of Gemini Flash artificial intelligence for fast image creation and editing. The model provides access to features that were previously available only to Pro version users, such as using real-world knowledge, web search data, and creating infographics, charts, and data visualizations. Additionally, the model supports accurate text reproduction on images, translation, and localization.
Among the new features of Nano Banana 2 are the preservation of character consistency (up to five) and support for up to 14 objects within a single workflow. Developers also highlight improved execution of complex instructions and the ability to create images with different aspect ratios and resolutions from 512 pixels to 4K. Compared to previous versions, the new model delivers higher detail, improved lighting, and textures.
The new model will be integrated into a number of Google services, including:
| Gemini App | Replaces Nano Banana Pro in Fast, Thinking, and Pro modes |
| Google Search | AI Mode and Lens on mobile devices and browsers |
| AI Studio and Gemini API | In preview mode |
| Google Cloud Vertex AI | Access via Gemini API |
| Flow | Used as the default model |
| Google Ads | For creating advertising campaigns |
Google AI Pro and Ultra subscribers will still be able to use Nano Banana Pro for specific tasks. This update is an important step in expanding Google’s artificial intelligence functionality, making it more accessible and versatile for users across various platforms.
