Google releases image generation AI 'Nano Banana 2,' enabling faster and more accurate image generation
Google has released Nano Banana 2 (Gemini 3.1 Flash Image), an image generation AI. Nano Banana 2 is designed to make the advanced features of Nano Banana Pro (Gemini 3 Pro Image) available to a wider range of users, while enabling rapid editing and iteration like Nano Banana (Gemini 2.5 Flash Image).
Nano Banana 2: Google's latest AI image generation model
Nano Banana 2 leverages Gemini's real-world knowledge base, incorporating information and images from real-time web searches to more accurately depict specific subjects. This deeper understanding allows you to efficiently create infographics, illustrate notes, and visualize data.
It can also generate accurate, readable text within images, as well as translate and localize text, helping you share your ideas globally. It also features subject consistency, maintaining the likeness of up to five characters and the fidelity of up to 14 objects in a single workflow, allowing you to storyboard and build narratives without changing their appearance.
The specifications are also well-suited for use in production environments, with the ability to freely control resolutions from 512 pixels to 4K and various aspect ratios. Visual fidelity has also been greatly improved, delivering vivid lighting, rich textures, and sharp details at high speed. Enhanced response to instructions has also been achieved, allowing even the subtlest nuances in complex requests to be captured.
In terms of safety and transparency, the combination of SynthID technology and C2PA content authentication information allows users to better understand the context of how AI is used.
The Gemini app will introduce Nano Banana 2 as the primary image generation model across all models: Fast, Thinking, and Pro, replacing the previously used Nano Banana Pro. However, users with Google AI Pro and Ultra subscriptions will continue to have access to Nano Banana Pro for certain specialized tasks, and can generate images with the older model by selecting 'Restart with Pro' from the menu.
For developers and businesses, it is available in preview in AI Studio and Gemini API, including in Google Antigravity , and in preview in Google Cloud's Vertex AI via the Gemini API.
Nano Banana 2 has been designated as the new default model for the creative tool Flow , allowing all users to use its generation features without consuming additional credits, and has also been introduced in Google Ads as a technology to help suggest assets when creating campaigns.
Additionally, Google Search will introduce Nano Banana 2 to AI mode, Google Lens, the Google app, mobile browser, and desktop browser. Eight new languages, including Japanese, have been added to the list of supported countries and regions, and 141 new countries and regions have been added.
Related Posts:
in AI, Web Service, Design, Creation, Posted by log1i_yk