Google has launched the next iteration of its Nano Banana artificial intelligence-powered visual generation model with Nano Banana 2, which incorporates various image generation tools into a single, more powerful platform.
With Nano Banana 2 (also called Gemini 3.1 Flash Image), Google has merged the capabilities of its Nano Banana and Nano Banana Pro models, bringing its most advanced image generation tools into a single app. Google said Nano Banana 2 will facilitate advanced world knowledge, quality and reasoning within its image generation capacity, and do so at lightning-fast speed.
As per Google: “[Nano Banana 2] pulls from Gemini’s real-world knowledge base, and is powered by real-time information and images from web search to more accurately render specific subjects. This deep understanding also helps you create infographics, turn notes into diagrams and generate data visualizations.”
Google said Nano Banana 2 will also be able to generate accurate, legible text for marketing mock-ups or greeting cards, as well as translate and localize text within an image.
The updated model also includes more specific controls, so that social media marketers can edit and update outputs as required to create more consistent, customized visuals.
Google said Nano Banana 2 can maintain character resemblance of up to five characters, as well as the fidelity of up to 14 objects in a single workflow. Meanwhile, the model is also able to adhere more strictly to complex requests, “capturing the specific nuances of your idea so the image you get is the image you asked for.”
Users will also be able to control the aspect ratios and resolutions of their outputs. In addition, Nano Banana 2 will provide richer textures and sharper details in generated content.
There are also new templates for different applications, including promotional images, and specific tools to help advertisers generate better visuals for campaigns.
It could be a handy tool, utilizing Google’s evolving AI generation models to create more standout, realistic-looking imagery. However, the shift away from more human-based, authentic interaction and engagement has not been a winner on all fronts, and brands do need to be aware of the potential downfalls of such in their own AI generations.
There is an inherent risk in brands using AI-generated content for marketing, in that some viewers will have a negative response to the artificial generations. AI visuals can also make it seem like brands are trying to cut corners by using AI tools, as opposed to hiring real creators (and if they’d be willing to cut costs here, where else will the brand be looking to cut corners?). There have also been increasing reports of broader backlash and negative responses to the deluge of AI-generated materials.
Indeed, a recent study published by Science Direct found that “customers perceive companies using AI-generated images as impersonal, less professional, lacking credibility, and potentially misleading, as they impede customers’ ability to envision the actual experience.”
Google itself was forced to change its approach to AI in advertising in 2024, after consumer backlash to an ad that depicted a father explaining how he asked Google’s Gemini AI bot to help his daughter write a letter to American Olympic hurdler Sydney McLaughlin-Levrone.
But more accurate, realistic-looking depictions will help with that, and Google said Nano Banana 2 can produce better visuals along those lines.
Nano Banana 2 is rolling out Feb. 26 across Google products, including the Gemini app, AI Mode in Google Search, Flow and Google Ads.
