“Nano Banana,” Google Gemini’s New AI-Powered Photo Editing Tool
Gemini, formerly known as Google Bard, is a conversational bot of multimodal and generative artificial intelligence developed by Google based on the Gemini Pro family. Although popularly known only as an AI response generator or image generator, it’s really a program that was developed as a direct response to OpenAI’s ChatGPT boom, owned by Elon Musk.
It was launched in March 2023 with an unenthusiastic welcome, as more than a year earlier, ChatGPT had already broken into the scene, becoming a global phenomenon. In just five days, Musk’s model had already gained a million users. Due to the company’s fear of violating the European Data Protection Regulation (GDPR), Gemini delayed its implementation on that continent until July of that year.
However, today the reality is very different. Gemini is established as a multimodal language model, developed by Google DeepMind, within reach of millions of people. His models of Gemini Nano, Gemini Pro, and Gemini Ultra have an agreement with Samsung and its Galaxy S smartphone line, fiercely competing against OpenAI’s GPT-4, an ally of Apple and its iPhone models.
One day in and our community is going #nanobanana over Gemini’s state-of-the-art image & editing update.
Here’s a round up of some outputs that caught our eyes:
— Google Gemini App (@GeminiApp) August 27, 2025
Nano Banana, the new improvement in photo editing
Google has presented Gemini 2.5 Flash Image, its new model of generation and edition of cutting-edge images, which includes capabilities to combine several images into one, maintaining the coherence of the characters that appear, as well as making specific transformations with natural language, all through the Gemini and Google application AI Studio.
In April 2025, Vertex AI was designed as a hybrid option by allowing you to activate or disable your reasoning capabilities to find the right balance between the quality of your answers, cost, and latency.
Noto to offer a better image editing experience for both developers and users in Gemini’s application, with higher quality results and more powerful creative control, Google welcomes you to “Nano Banana.”
What is Nano Banana?
This model allows you to combine several images in one, all maintaining the coherence of the characters or objects that are included. It also allows specific transformations of images by natural language (talking or writing).
As the company has detailed in a statement on its developer blog, these capabilities have been implemented in the creation model of Google AI Studio as a test. So developers can remix or give life to their ideas with a single instruction in natural language and share them later in Google AI Studio.
The edition of native images in the Gemini app for all users has also been updated in order to improve editing capabilities and maintain the similarity between the images. The intention is to create a representation almost identical to the original photo.
How to edit photos with Nano Banana?
It will be enough to share with Gemini a photo to edit specific issues and give it a unique touch. For example, requesting that the person in the photo appear in new scenarios, but maintaining their original appearance in each image.
According to Google, Gemini can also vary people’s outfits and professions in photography, even reimagining them in another era without losing their identity. In the same way, users can also merge photos, sharing several images and attaching them to one to create a completely new scene.
In addition to all this, you can also request concrete modifications of images, such as changing the color of the walls of a room or adding furniture, keeping the rest of the image intact. However, all images created or edited in Gemini’s app include a visible watermark.
How to get Gemini’s Nano Banana?
This update does a much better job, allowing the edits to be more fluid, and the results of the model can be used for whatever you want, said the product director in visual generation models at Google DeepMind, Nicole Brichtova, in statements to TechCrunch.
Finally, the Gemini 2.5 Flash Image is already available through the Gemini API and Google AI Studio for developers, as well as through Vertex AI for companies. This new update costs $30.
This money is used to acquire a million outlet tokens, a kind of virtual currency within Google Gemini, which is enough to generate approximately 775 images. Which means the image made with Nano Banana costs about 50 cents.
