Google launched Gemini 2.5 Flash Picture, a brand new mannequin that many beta customers knew as nanobanana, which supplies enterprises extra selection for inventive tasks. It allows them to vary the look of pictures they want shortly and with extra management than what earlier fashions supplied.

The mannequin shall be built-in into the Gemini app. 

The mannequin, constructed on prime of Gemini 2.5 Flash, provides extra capabilities to the native picture enhancing on the Gemini app. Gemini 2.5 Flash Picture maintains character likenesses between totally different pictures and has extra consistency when enhancing footage. If a consumer uploads a photograph of their pet after which asks the mannequin to vary the background or add a hat to their canine, Gemini 2.5 Flash Picture will do this with out altering the topic of the image. 

“We all know that when enhancing footage of your self or folks you already know effectively, delicate flaws matter, an outline that’s ‘shut however not fairly the identical’ doesn’t really feel proper,” Google stated in a weblog publish written by Gemini Apps multimodal technology lead David Sharon and Google DeepMind Gemini picture product lead Nicole Brichtova. “That’s why our newest replace is designed to make photographs of your mates, household and even your pets look persistently like themselves.” 

One criticism enterprises and a few particular person customers had is that when prompting edits on AI-generated pictures, slight tweaks alter the photograph an excessive amount of. For instance, somebody could instruct the mannequin to maneuver an individual’s place within the image, and whereas the mannequin does what it’s informed, the particular person’s face is altered barely. 

All pictures generated on Gemini will embrace Google’s SynthID watermark. The mannequin is out there for all paid and free customers of the Gemini app. 

Hypothesis that Google plans to launch a brand new picture mannequin ran rampant on social media platforms. Customers on LM Enviornment noticed a mysterious new mannequin referred to as nanobanana that adopted “advanced, multistep directions with spectacular accuracy,” as Andressen Horowitz associate Justine Moore put it in a publish. 

Mysterious new picture edit mannequin hit the sector ?

“Nano-banana” enables you to add TWO pictures and immediate to mix them.

It may well comply with advanced, multi-step directions with spectacular accuracy. pic.twitter.com/Ylu54w7ge4

— Justine Moore (@venturetwins) August 17, 2025

Folks quickly seen that the nanobanana mannequin appeared to come back from Google earlier than a number of early testers confirmed it. Although on the time, Google didn’t verify what it deliberate to do with the mannequin on LM Enviornment. 

Nano-banana is BANANAS! ?

Critically, it took simply my profile pic and this immediate: “Medium shot of the person dealing with the digital camera enjoying guitar on a stage in a bar”

What mannequin is that this? I’m betting Imagen 5! ? Any guesses? pic.twitter.com/SAQRcdW2zL

— Anis Aydar (@anisaydar) August 15, 2025

Google’s Nanobanana ? is concerning the drop an AI mannequin that delivers pro-level Photoshop edits in seconds, with solely textual content.

This the subsequent technology of what “filters” we have been promised ceaselessly.

Here is a thread of 10 examples:

Altering facial expressions and the climate.

1/11 pic.twitter.com/M8WCf7JFNT

— Deedy (@deedydas) August 23, 2025

Up till this week, hypothesis on when the mannequin would come out continued, which is prophetic in a means.

A lot of the joy comes because the combat between mannequin suppliers to supply extra succesful and real looking pictures and edits, exhibiting how highly effective multimodal fashions have turn out to be. 

Nevertheless, Google nonetheless must combat off rivals like Qwen and its just lately launched Qwen-Image Edit and OpenAI, which added native AI picture enhancing to ChatGPT and in addition made the model available as an API. 

After all, Adobe, lengthy thought-about one of many leaders within the picture enhancing area, added its flagship model Firefly to Photoshop and its different photograph enhancing platforms. 

Native picture enhancing 

Gemini added native AI image editing on Gemini in March, which it supplied to free customers of the chat platform. 

Bringing picture enhancing options straight into the chat platform would enable enterprises to repair pictures or graphs with out shifting home windows. 

Customers can add a photograph to Gemini, then inform the mannequin what modifications they need. As soon as they’re glad, the brand new footage will be reuploaded to Gemini and made right into a video. 

Apart from including a dressing up or a location change, Gemini 2.5 Flash Picture can mix totally different photographs, gives multi-turn enhancing and blend types of 1 image to a different.

Day by day insights on enterprise use circumstances with VB Day by day

If you wish to impress your boss, VB Day by day has you lined. We provide the inside scoop on what firms are doing with generative AI, from regulatory shifts to sensible deployments, so you may share insights for max ROI.

Learn our Privacy Policy

Thanks for subscribing. Take a look at extra VB newsletters here.

An error occured.