Want smarter insights in your inbox? Sign up for our weekly newsletters to get only what matters to enterprise AI, data, and security leaders. Subscribe Now
Google’s highly speculated new image model, which many beta users know as nanobanana, has finally been released as Gemini 2.5 Flash Image and will be integrated into the Gemini app.
The new model would give enterprises more choice for creative projects and enable them to change the look of images they need quickly.
The model, built on top of Gemini 2.5 Flash, adds more capabilities to the native image editing on the Gemini app. Gemini 2.5 Flash Image maintains character likenesses between different images and has more consistency when editing pictures. If a user uploads a photo of their pet and then asks the model to change the background or add a hat to their dog, Gemini 2.5 Flash Image will do that without altering the subject of the picture.
“We know that when editing pictures of yourself or people you know well, subtle flaws matter, a depiction that’s ‘close but not quite the same’ doesn’t feel right,” Google said in a blog post written by Gemini Apps multimodal generation lead David Sharon and Google DeepMind Gemini image product lead Nicole Brichtova. “That’s why our latest update is designed to make photos of your friends, family and even your pets look consistently like themselves.”
AI Scaling Hits Its Limits Power caps, rising token costs, and inference delays are reshaping enterprise AI. Join our exclusive salon to discover how top teams are: Turning energy into a strategic advantage
Architecting efficient inference for real throughput gains
Unlocking competitive ROI with sustainable AI systems Secure your spot to stay ahead: https://bit.ly/4mwGngO
One complaint enterprises and some individual users had is that when prompting edits on AI-generated images, slight tweaks alter the photo too much. For example, someone may instruct the model to move a person’s position in the picture, and while the model does what it’s told, the person’s face is altered slightly.
All images generated on Gemini will include Google’s SynthID watermark. The model is available for all paid and free users of the Gemini app.
Social media excitement
Speculation that Google plans to release a new image model ran rampant on social media platforms. Users on LM Arena saw a mysterious new model called nanobanana that followed “complex, multistep instructions with impressive accuracy,” as Andressen Horowitz partner Justine Moore put it in a post.
Mysterious new image edit model hit the arena ?
"Nano-banana" lets you upload TWO images and prompt to combine them.
It can follow complex, multi-step instructions with impressive accuracy. pic.twitter.com/Ylu54w7ge4 — Justine Moore (@venturetwins) August 17, 2025
People soon noticed that the nanobanana model seemed to come from Google before several early testers confirmed it. Though at the time, Google did not confirm what it planned to do with the model on LM Arena.
We're 99.9% sure nano-banana is from Google.
Video by @Kling_ai with the new first/last frame early access for their 2.1 model.
Looks amazing: pic.twitter.com/MWjvWge3Te — Alex Patrascu (@maxescu) August 19, 2025
Nano-banana is BANANAS! ?
Seriously, it took just my profile pic and this prompt: "Medium shot of the man facing the camera playing guitar on a stage in a bar"
What model is this? I’m betting Imagen 5! ? Any guesses? pic.twitter.com/SAQRcdW2zL — Anis Aydar (@anisaydar) August 15, 2025
Google’s Nanobanana ? is about the drop an AI model that delivers pro-level Photoshop edits in seconds, with only text.
This the next generation of what "filters" we've been promised forever.
Here's a thread of 10 examples:
Changing facial expressions and the weather.
1/11 pic.twitter.com/M8WCf7JFNT — Deedy (@deedydas) August 23, 2025
Up until this week, speculation on when the model would come out continued, which is prophetic in a way.
Much of the excitement comes as the fight between model providers to offer more capable and realistic images and edits, showing how powerful multimodal models have become.
However, Google still needs to fight off rivals like Qwen and its recently released Qwen-Image Edit and OpenAI, which added native AI image editing to ChatGPT and also made the model available as an API.
Of course, Adobe, long considered one of the leaders in the image editing space, added its flagship model Firefly to Photoshop and its other photo editing platforms.
Native image editing
Gemini added native AI image editing on Gemini in March, which it offered to free users of the chat platform.
Bringing image editing features directly into the chat platform would allow enterprises to fix images or graphs without moving windows.
Users can upload a photo to Gemini, then tell the model what changes they want. Once they are satisfied, the new pictures can be reuploaded to Gemini and made into a video.
Other than adding a costume or a location change, Gemini 2.5 Flash Image can blend different photos, offers multi-turn editing and mix styles of one picture to another.