Google's Nano Banana 2 is a faster version of Nano Banana Pro

Source: Engadget

Overview

Google has launched its new image generation model, Nano Banana 2, which is powered by Gemini 3.1 Flash Image. The company says the new model has the capabilities, world knowledge, and reasoning of Nano Banana Pro, but it can accomplish tasks at “lightning‑fast speed.” This enables rapid editing and quick creation of various iterations using a single prompt.

New Capabilities

• Access to features previously exclusive to the Pro model, including the ability to pull real‑time information and images from web searches for creating infographics and diagrams.
• Generation of text on images for marketing materials and greeting cards.
• Maintenance of character resemblance for up to five characters in a single workflow, useful for storyboards or visual stories.
• Precise instruction following for complex requests.
• Output resolution up to 4K with richer textures and sharper details than earlier versions.

Comparison with Nano Banana Pro

Nano Banana Pro could already generate images so realistic that they were almost indistinguishable from real photos, leading Google to limit its use due to high demand. Nano Banana 2 aims to improve speed and resolution, but whether it can consistently produce images markedly better than the Pro model—and whether the AI origin will remain detectable—remains to be seen.

Availability

• Nano Banana 2 will replace Nano Banana Pro in the Gemini app.
• Google AI Pro and Ultra subscribers will retain access to Nano Banana Pro for specialized tasks.
• The model will be the default in Search for AI Mode, Lens, and Google’s Flow AI creative studio.

This article originally appeared on Engadget: https://www.engadget.com/ai/googles-nano-banana-2-is-a-faster-version-of-nano-banana-pro-160000695.html?src=rss