Google rolls out Nano Banana 2 with faster, high-fidelity image generation for all users

Google has launched Nano Banana 2, an upgraded image generation model designed to support advanced world knowledge, production-ready visual specifications, and improved subject consistency. This release integrates the high-speed intelligence of Gemini Flash, enabling rapid iterations and efficient editing in the creative workflow. Advanced capabilities previously limited to Pro users, including rich world context and detailed editing tools, are now accessible to a wider audience.

In addition to leveraging real-world data and images from web search for more accurate subject representation, Nano Banana 2 can create infographics, turn notes into diagrams, and generate data visualizations. Its text rendering features allow for the production of accurate, legible, and translatable image text, addressing the needs of marketing and international communication. Users can expect high-fidelity, photorealistic images and a model that adheres closely to complex instructions, ensuring generated visuals align with specific requirements.

Following these core improvements, Nano Banana 2 maintains the visual consistency of up to five distinct characters and the fidelity of up to 14 objects in a single workflow, important for narrative and storyboard creation. Production-ready specifications provide flexible output, supporting a range of aspect ratios and resolutions from 512 pixels to 4K, while lighting, texture, and detail are enhanced without compromising speed. The model is available in multiple Google products, including the Gemini app, AI Mode and Lens in Google Search, Google AI Studio, Vertex AI, Antigravity, Flow, |Google Ads, and via the API.