Google DeepMind Unveils 'Nano Banana' AI Model, Revolutionizing Image Editing in Gemini

Google improves Gemini AI image editing with "nano banana" model

Something unusual happened in the world of AI image editing recently. A new model, known as "nano banana," started making the rounds with impressive abilities that landed it at the top of the LMArena leaderboard. Now, Google has revealed that nano banana is an innovation from Google DeepMind, and it's being rolled out to the Gemini app today. AI image editing allows you to modify images with a prompt rather than mucking around in Photoshop. Google first provided editing capabilities in Gemini earlier this year, and the model was more than competent out of the gate. But like all generative systems, the non-deterministic nature meant that elements of the image would often change in unpredictable ways. Google says nano banana (technically Gemini 2.5 Flash Image) has unrivaled consistency across edits -- it can actually remember the details instead of rolling the dice every time you make a change. This unlocks several interesting uses for AI image editing. Google suggests uploading a photo of a person and changing their style or attire. For example, you can reimagine someone as a matador or a '90s sitcom character. Because the nano banana model can maintain consistency through edits, the results should still look like the person in the original source image. This is also the case when you make multiple edits in a row. Google says that even down the line, the results should look like the original source material. Gemini's enhanced image editing can also merge multiple images, allowing you to use them as the fodder for a new image of your choosing. Google's example below takes separate images of a woman and a dog and uses them to generate a new snapshot of the dog getting cuddles -- possibly the best use of generative AI yet. Gemini image editing can also merge things in more abstract ways and will follow your prompts to create just about anything that doesn't run afoul of the model's guardrails. As with other Google AI image generation models, the output of Gemini 2.5 Flash Image always comes with a visible "AI" watermark in the corner. The image also has an invisible SynthID digital watermark that can be detected even after moderate modification. You can give the new native image editing a shot today in the Gemini app. Google says the new image model will also roll out soon in the Gemini API, AI Studio, and Vertex AI for developers.

Google Gemini's AI image model gets a 'bananas' upgrade | TechCrunch

Google is upgrading its Gemini chatbot with a new AI image model that gives users finer control over editing photos, a step meant to catch up with OpenAI's popular image tools and draw users from ChatGPT. The update, called Gemini 2.5 Flash Image, rolls out starting Tuesday to all users in the Gemini app, as well as to developers via the Gemini API, Google AI Studio, and Vertex AI platforms. Gemini's new AI image model is designed to make more precise edits to images -- based on natural language requests from users -- while preserving the consistency of faces, animals, and other details, something that most rival tools struggle with. For instance, ask ChatGPT or xAI's Grok to change the color of someone's shirt in a photo, and the result might include a distorted face or an altered background. Google's new tool has already drawn attention. In recent weeks, social media users raved over an impressive AI image editor in the crowdsourced evaluation platform, LMArena. The model appeared to users anonymously under the pseudonym "nano-banana." Google says it's behind the model (if it wasn't obvious already from all the banana-related hints), which is really the native image capability within its flagship Gemini 2.5 Flash AI model. Google says the image model is state-of-the-art on LMArena and other benchmarks. "We're really pushing visual quality forward, as well as the model's ability to follow instructions," said Nicole Brichtova, a product lead on visual generation models at Google DeepMind, in an interview with TechCrunch. "This update does a much better job making edits more seamlessly, and the models outputs are usable for whatever you want to use them for," said Brichtova. AI image models have become a critical battle ground for Big Tech. When OpenAI launched GPT-4o's native image generator in March, it drove ChatGPT's usage through the roof thanks to a frenzy of AI-generated Studio Ghibli memes that, according to OpenAI CEO Sam Altman, left the company's GPUs "melting." To keep up with OpenAI and Google, Meta announced last week that it would license AI image models from the startup Midjourney. Meanwhile, the a16z-backed German unicorn Black Forest Labs continues to dominate benchmarks with its FLUX AI image models. Perhaps Gemini's impressive AI image editor can help Google close its user gap with OpenAI. ChatGPT now logs more than 700 million weekly users. On Google's earnings call in July, the tech giant's CEO Sundar Pichai revealed that Gemini had 450 million monthly users -- implying weekly users are even lower. Brichtova says Google specifically designed the image model with consumer use cases in-mind, such as helping users visualize their home and garden projects. The model also has better "world knowledge" and can combine multiple references in a single prompt; for example, merging an image of a sofa, a living room photo, and a color palette into one cohesive render. While Gemini's new AI image generator makes it easier for users to make and edit realistic images, the company has safeguards that limit what users can create. Google has struggled with AI image generator safeguards in the past. At one point, the company apologized for Gemini generating historically inaccurate pictures of people, and rolled back the AI image generator altogether. Now, Google feels that it's struck a better balance. "We want to give users creative control so that they can get from the models what they want," said Brichtova. "But it's not like anything goes." The generative AI section of Google's terms of service prohibits users from generating "non-consensual intimate imagery." Those same kinds of safeguards don't seem to exist for Grok, which allowed users to create AI-generated explicit images resembling celebrities, such as Taylor Swift. To address the rise of deepfake imagery, which can make it hard for users to discern what's real online, Brichtova says that Google applies visual watermarks to AI-generated images, as well as identifiers in its metadata. However, someone scrolling past an image on social media may not look for such identifiers.

Google's New AI Image Model 'Bananas' Is Here: How to Edit Your Photos With Gemini

Google wants you to ditch Photoshop for Gemini. A new generative AI model, Gemini 2.5 Flash Image, upgrades Gemini's ability to edit your photos natively in the Gemini app. It's available now for all Gemini users, free and paying, and is rolling out in preview this week in the Gemini API and Google AI Studio and Vertex AI. A recent preview version of the new model on LMArena sparked interest from Gemini fans, even though the model only ranked seventh as of Monday, behind leaders like OpenAI's image model and Flux's Kontext Pro and Max. It's been referred to as the "nano bananas" model by AI enthusiasts, spurred on by a recent X post from Josh Woodward, Google's vice president of Google Labs and Google Gemini. You don't need to do anything to access the new model; it's automatically added to the base Gemini 2.5 Flash model. All you have to do is upload an image and type out your prompt, and Gemini will attempt to edit it. You should notice a difference when you ask Gemini to edit photos -- more precise edits and fewer errors from hallucinations. Adobe Express and Firefly users can also access the new model now. Some new features include the ability to replace backgrounds and layer multiple edits. You can also combine different elements with "design remix." For example, you can upload an image of a pair of rain boots and a pink rose, and Gemini will reimagine the rain boots in a floral pattern echoing the pink rose. You can also blend two photos together, creating a kind of composite image. Google's Gemini privacy policy says it can use the information you upload for improving its AI products, which is why the company recommends avoiding uploading sensitive or private information. The company's AI prohibitive use policy also outlaws the creation of illegal or abusive material. Google has been investing heavily in its generative media models this year, dropping updated versions of its image and video generator models at its annual I/O developers conference. Google's AI video generator Veo 3 stunned with synchronized audio, a first among the bevy of AI giants. Creators have made more than 100 million AI videos with Google's AI filmmaker tool, Flow. NotebookLM, an experimental product from Google Labs, also took off in popularity with its ability to turn any set of documents into a personalized podcast.

Top-rated mystery 'nano-banana' AI model rolls out to Gemini, as Google DeepMind claims responsibility

Google DeepMind was secretly behind the model, which is now publicly available. Every now and then, the LMArena will have a mystery model with a fun name shoot up to the top of the leaderboard. Shall I remind you of OpenAI's Project Strawberry? More recently, a mystery 'nano banana' model climbed to the top of the LMArena's photo-editing models on early previews (where it still resides), earning the title of 'top-rated image editing model in the world,' and you can now access it today. Also: You can now add AI images directly into LibreOffice documents - here's how On Tuesday, Google DeepMind revealed that it was responsible for the high-performing photo editing 'nano banana' model. With the model, users can edit pictures using natural language prompts while keeping the essence of the image intact better than ever before, and it is being integrated right in the Gemini app. If you have ever uploaded an image of yourself into an AI image generator and asked it to create a new version of it in some way, for example, making it a watercolor version of yourself or anime, you may have noticed that your features sometimes don't get lost in translation. This new model aims to change that, making the subject, whether it is a pet or a person, look like themselves. Google suggests putting photo editing to the test by changing your clothing or giving yourself a costume, or even changing your location entirely. As seen in the GIF below, the edited version keeps the person's appearance the same amidst outfit changes. These edits are more entertaining, but the AI editing tool can also be used for more practical edits. For example, you can take elements of two different photos and blend them together to create a new one. Google shares an example of a solo shot of a woman being combined with a short solo shot of a dog to make it look like they are cuddling. In a way, it is like everyone gets access to the Add Me feature that Google has been offering on its Pixel phones. Also: How a Meta partnership with Midjourney could inject more AI into future products With the model, you can also take advantage of multi-turn edits, in which you keep using prompts to tweak an element of the same photo until you get the intended result, such as adding different pieces of furniture to a room or adding different elements to the background of your photo. You can also take elements of one photo, such as a color, and apply them to a new image. The updated image editing is already available in the Gemini app starting today. All you need to do is enter your prompt to get started. Like all Gemini-generated images, images created or edited with this updated model will have the SynthID digital watermark, delineating that they are AI-modified.

Google DeepMind claims top-rated 'banana' mystery model - here's what it can do

Google DeepMind was secretly behind the model, which is now publicly available. Every now and then, the LMArena will have a mystery model with a fun name shoot up to the top of the leaderboard. Shall I remind you of OpenAI's Project Strawberry? More recently, a mystery 'nano banana' model climbed to the top of the LMArena's photo-editing models on early previews, earning the title of 'top-rated image editing model in the world,' and you can now access it today. Also: You can now add AI images directly into LibreOffice documents - here's how On Tuesday, Google DeepMind revealed that it was responsible for the high-performing photo editing 'nano banana' model. With the model, users can edit pictures using natural language prompts while keeping the essence of the image intact better than ever before, and it is being integrated right in the Gemini app. If you have ever uploaded an image of yourself into an AI image generator and asked it to create a new version of it in some way, for example, making it a watercolor version of yourself or anime, you may have noticed that your features sometimes don't get lost in translation. This new model aims to change that, making the subject, whether it is a pet or a person, look like themselves. Google suggests putting photo editing to the test by changing your clothing or giving yourself a costume, or even changing your location entirely. As seen in the GIF below, the edited version keeps the person's appearance the same amidst outfit changes. These edits are more entertaining, but the AI editing tool can also be used for more practical edits. For example, you can take elements of two different photos and blend them together to create a new one. Google shares an example of a solo shot of a woman being combined with a short solo shot of a dog to make it look like they are cuddling. In a way, it is like everyone gets access to the Add Me feature that Google has been offering on its Pixel phones. Also: How a Meta partnership with Midjourney could inject more AI into future products With the model, you can also take advantage of multi-turn edits, in which you keep using prompts to tweak an element of the same photo until you get the intended result, such as adding different pieces of furniture to a room or adding different elements to the background of your photo. You can also take elements of one photo, such as a color, and apply them to a new image. The updated image editing is already available in the Gemini app starting today. All you need to do is enter your prompt to get started. Like all Gemini-generated images, images created or edited with this updated model will have the SynthID digital watermark, delineating that they are AI-modified.

Google Gemini 2.5 Flash Image (Nano Bananas) is quite good

Google has updated its Gemini AI image generation tool with a build that caused a stir after it was released under the code name Nano Bananas. The upgrade, technically called Gemini 2.5 Flash Image, lets users generate images through voice and text prompts, including swapping out participants in a photo, changing what they are wearing, or merging people from real images with new backgrounds. Google formally released it on Tuesday, though only via the Gemini mobile app, with the web version not getting all the new capabilities yet. We've been testing the new engine and the results are impressive. For example, Reg US Editor Avram Piltch took a photo of just his torso and a separate photo of two chairs. When he uploaded both photos to Gemini on his phone, he asked the engine to draw him seated in the red chair. Gemini not only placed Piltch in the red chair, but drew arms and legs for him that weren't in the original torso picture. It even completed the logo on his t-shirt that was only half visible in the original image. The only inaccurate thing about the merged photo was that his pants were black when, in real life, he was wearing blue jeans. He asked Gemini to change the pants to light blue jeans, and it did so without issue. "Just give Gemini a photo to work with, and tell it what you'd like to change to add your unique touch. Gemini lets you combine photos to put yourself in a picture with your pet, change the background of a room to preview new wallpaper or place yourself anywhere in the world you can imagine -- all while keeping you, you," the Chocolate Factory said. "Once you're done, you can even upload your edited image back into Gemini to turn your new photo into a fun video." In other tests, Piltch was took a picture of his daughter and asked that two statues next to her be removed. The statues disappeared with the shadow from a nearby tree extending to where they were before. He then asked that his daughter appear in front of the pyramids and Gemini obliged, even changing her posture so she was standing straighter. One major improvement users will notice right off the bat is how fast it is. In tests, images were done in seconds, with all the work taking place in the cloud. (Admittedly, we were using an older Pixel.) We even made the bananas cover art for this piece using Gemini. In a move that should have Adobe worried, Gemini shows real skill in letting image editors use AI to replace in seconds what might have taken a graphic designer hours, or at least minutes. Where you used to have to Photoshop someone into a picture, now you can just ask the tool to do it for you. Google has included a SynthID watermark to allow someone to identify the AI-generated images, which should be a big help in cutting down on fake pictures for spam, incitement, or for other purposes. That's not going to stop a wave of AI-generated spam shortly to be hitting your inboxes, but it will at least provide some safety checks. There are still some guardrails in Gemini 2.5 Flash Image, although they are somewhat limited. Generating pictures of Hitler, for example, is difficult but not impossible. If you want a celebrity such as Taylor Swift or Donald Trump, you won't have any problems, though. It does at least have safeguards against generating images of a pornographic bent, thankfully. Overall, while some images came out less than perfect, it's still a worthy rival to other LLM image designers from OpenAI or xAI's Grok. Google is rolling out the new system for Gemini API, Google AI Studio for developers, and Vertex AI, at a cost of $30 per one million output tokens, with each image being 1290 output tokens ($0.039 per image). This is very much an interim build, Google said, with more improvements coming down the line. It's also partnered with OpenRouter.ai and fal.ai to make the technology more accessible. It'll now be up to other AI companies to match Google's very compelling new feature set. ®

Mysterious 'Nano-Banana' Project Revealed to Be Google's Latest Image Editor

The tech giant came forward as the creator of the viral nano-banana AI image model. Google just upgraded its AI image model, and it actually looks to be a pretty significant step up. The company rolled out Gemini 2.5 Flash Image today, a major refresh that promises smarter and more flexible image generation. The upgraded model allows users to issue natural language prompts to not only generate images but also merge existing photos and make more precise edits without creating weird distortions. It also taps into Gemini’s “world knowledge†to better understand what it’s generating. This upgrade comes as Google tries to close the gap with the industry leader, OpenAI. In the past, image generation has been a major driver for AI. ChatGPT usage skyrocketed in March when the company launched its GPT-4o native image generator. The viral Studio Ghibli memes generated by the model resulted in the company's GPU models melting, according to OpenAI CEO Sam Altman. ChatGPT currently has over 700 million weekly users. By comparison, Google CEO Sundar Pichai revealed on the company’s July earnings call that Gemini had 450 million monthly users, still trailing behind ChatGPT. With its latest update, Google says it’s solved one of AI's biggest headaches. Until now, keeping characters or objects consistent across multiple edits has been a major challenge for AI image generators. "You can now place the same character into different environments, showcase a single product from multiple angles in new settings, or generate consistent brand assets, all while preserving the subject," the company wrote in a blog post. Google says users can now make very specific tweaks with just a prompt. For example, users can blur the background of an image, remove a stain from a T-shirt, change a subject’s pose, or even add color to a black-and-white photo. Even before its official launch, the new model was turning heads on the crowdsourced evaluation platform LMArena, where it appeared anonymously under the name “nano-banana.†One X user shared how they used nano-banana to change Altman’s shirt in a photo. The result was surprisingly good. Today, Google stepped forward and claimed ownership of the model, revealing that nano-banana was in fact Gemini 2.5 Flash Image. In addition to being available on the Gemini app, the new model is now accessible to developers through the Gemini API, Google AI Studio, and Vertex AI. Google has already built several template apps that make use of the new model on Google AI Studio, the company's coding AI assistant, and said users can vibe code on top of them. The company also said some developers have already experimented with the app to see how it would be useful in real-world scenarios, like creating real estate listing cards, employee uniform badges, and product mockups.

Gemini expands image editing for enterprises: Consistency, collaboration, and control at scale

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." 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. 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. 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. 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. 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.

Google aims to be top banana in AI image editing

Why it matters: Nano Banana is the latest in a series of image-editing tools that have captured the internet's public eye, impressing users with its ability not only to generate new images but to refine them -- a skill that has proven elusive to AI makers. Driving the news: Google said the model that had been making waves under its code name will be available starting Tuesday to free and paid Gemini users on the web and in its mobile apps. * For now, free users can create up to 100 image edits per day, while paid users can make ten times as many edits with the tool, officially dubbed Gemini 2.5 Flash Image. * Under the Nano Banana name, the model had already been outperforming other models on the LMArena charts for image editing and generating significant buzz on social media. How it works: The new tool lets people create a photo from text or based on an existing image. * Google provided a reference photo of a young woman which the tool then transformed by putting her in matador garb. Google says the model is also better than prior models at multi-step edits. * In one example, Google shows a variety of stages of a room renovation being imagined, first with a fresh coat of paint and later with the addition of various pieces of furniture. The tool can also combine two images. * Google showed an example of one image getting transformed into a pattern that was then applied onto boots in another photo. * The model's creations are labeled as AI-generated using Google's SynthID watermarking system. Between the lines: While AI has proved helpful at generating images, it has tended to falter in the editing stage, particularly when asked to make changes to photos of real people. * Google says its new tool is better than its and others' previous models at making sure the subject of a photo doesn't start to look like someone else, especially as edits pile up. * "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. * "That's why our latest update is designed to make photos of your friends, family and even your pets look consistently like themselves, whether you're trying out a '60s beehive haircut or putting a tutu on your chihuahua." Flashback: OpenAI saw a surge of ChatGPT downloads and usage after it released a highly capable image generator in March. Yes, but: The more Google and its rivals refine their AI tools' ability to combine images or display people in new settings, the greater the threat of users creating deepfakes and misinformation.

Google Boosts Gemini AI Image Capabilities in Latest Salvo Against ChatGPT - Decrypt

Google has expanded access through OpenRouter and fal.ai, widening distribution to coders worldwide. Google launched Gemini 2.5 Flash Image on Tuesday, delivering a new AI model that generates and edits images with more precision and character consistency than previous tools -- attempting to close the gap with OpenAI's ChatGPT. The tech giant's push to integrate advanced image editing into Gemini reflects a broader push among AI platforms to include image generation as a must-have feature. The new tool, now available across Gemini apps and platforms, lets users edit visuals using natural language -- handling complex tasks like pose changes or multi-image fusion without distorting faces or scenes. In a blog post, Google said the model allows users to "place the same character into different environments, [and] showcase a single product from multiple angles... all while preserving the subject." The model first appeared under the pseudonym "nano-banana" on crowdsourced testing site LMArena, where it drew attention for its seamless editing. Google confirmed Tuesday it was behind the tool. Google said the system can fuse multiple images, maintain character consistency for storytelling or branding, and integrate "world knowledge" to interpret diagrams or combine reference materials -- all within a single prompt. The model costs $30 per million output tokens -- about four cents per image -- on Google Cloud. It's also being distributed via OpenRouter and fal.ai. OpenAI introduced the GPT-4o model in May 2024 and added image generation in March 2025, which helped push ChatGPT's usage above 700 million weekly active users. Google reported 400 million monthly active Gemini users in August 2025, which would indicate weekly usage that considerably trails OpenAI. Google said all outputs will include an invisible SynthID watermark and metadata tag to mark them as AI-generated to address concerns around misuse and authenticity.

Google Unveils 'Nano-Banana' Image Model With Editing and Fusion Features | AIM

The model is priced at $30 per 1 million output tokens, with each image costing 1,290 tokens, or $0.039 per image. Google has announced the launch of Gemini 2.5 Flash Image, aka nano-banana, its latest image generation and editing model, now available through the Gemini API, Google AI Studio, and Vertex AI for enterprise. The company said the model allows users to blend multiple images, maintain character consistency across edits, perform targeted transformations with natural language prompts, and leverage Gemini's built-in world knowledge. "When we first launched native image generation in Gemini 2.0 Flash earlier this year, you told us you loved its low latency, cost-effectiveness, and ease of use. But you also gave us feedback that you needed higher-quality images and more powerful creative control," Google said in its announcement. The model is priced at $30 per 1 million output toke

Google updates Gemini with powerful new AI image model with photo editing capabilities - SiliconANGLE

Google LLC said today its updating its Gemini app and chatbot with a powerful new artificial intelligence image model that will allow users fine-grained photo editing capabilities. The new model, named Gemini 2.5 Flash Image, debuts today on the Gemini app so that users can start using it to edit their photos with natural language. The company claims that the new model provides state-of-the-art image generation and editing for photos, keeping the original composition, objects and people intact while adding, changing or removing whatever the user wants. Google DeepMind, the company's AI research arm, tested the new model under the mysteriously silly name "Nano Banana" on LMArena. This public site crowdsources anonymous feedback on AI model quality. At first, it was unknown what this new model might be, especially given its weird name, but users quickly sussed out that it must be from Google. The model outperformed every other photo-editing model on the site in early preview, gaining it the title of "top-rated editing model in the world." Although it was not without its flaws, the model proved to be superior for consistency, quality and following instructions. Now, DeepMind has revealed that the model is actually Gemini 2.5 Flash Image and powers the new Gemini image editing experience. "We're really pushing visual quality forward, as well as the model's ability to follow instructions," said Nicole Brichtova, a product lead on visual generation models at Google DeepMind, in an interview with TechCrunch. One of the problems for image editing and AI models has always been that models tend to make subtle or large modifications to images, even when users ask them to make small changes. For example, a user might take a photograph of themselves and ask a model to add glasses. The model might add glasses to their face, but it could dramatically change their features, adjust their hairstyle or an object in the background might change from one thing to another. To test out the new model, Google suggested that people try it out with a photo of themselves. They could use it to put themselves in a new outfit or change their location. The model is also capable of blending subjects from two different photos into a brand-new scene. For example, taking a picture of your cat and you and having it put you together on the couch. According to Google, this new model allows users to make multi-turn edits. Just take a photo and ask for one change and then follow up with another. This allows for iterative modifications to photos or images that feel natural. Since prompts can make specific requests about locations or subjects, the model will only change them and nothing else. Developers can also get access to this capability through Google's AI platforms and tools via Gemini API, Google AI Studio and Vertex AI. In addition to the news of the release, Adobe Inc. announced that it will add the new model to its AI-powered Firefly app and Adobe Express, making it easier for users to use the model to modify their photos and create stylized graphics with a consistent look and feel.

Why Google's New AI Image Generator Could Give OpenAI a Run for Its Money

Google just dropped a major update for its AI image generation tech, enabling anyone to generate images with more accurate outcomes. In a blog post, Google revealed Gemini 2.5 Flash Image (also called nano-banana), its latest and greatest AI model for generating and editing images. Google says the new model gives users the ability to blend multiple images into a single image, maintain character consistency across multiple generations, and make more granular tweaks to specific parts of an image. One of the model's new features is that ability to maintain character consistency, meaning that if you create a specific look for an AI-generated character, the character will maintain that look each time you generate a new image featuring them. "You can now place the same character into different environments," Google wrote, "showcase a single product from multiple angles in new settings, or generate consistent brand assets, all while preserving the subject." Gemini 2.5 Flash Image can also make more granular edits to images, like blurring a background, and changing the color of an item of clothing.

Google unveils Gemini 2.5 Flash Image upgrade - The Economic Times

Google on Tuesday unveiled Gemini 2.5 Flash Image, also called the Nano-Banana image generation and editing model available via the Gemini API and Google AI Studio for developers and Vertex AI for enterprise.Google has introduced an upgrade to its Gemini chatbot with a new image generation and editing model, giving users more control over modifying photos. The update, named Gemini 2.5 Flash Image, became available Tuesday across the Gemini app and to developers through the Gemini API, Google AI Studio, and Vertex AI, CEO Sundar Pichai said in a post on X. Nano-banana upgrade The feature allows users to: Gemini 2.5 Flash Image The news comes after Google launched Gemini 2.0 Flash, its most advanced suite of AI models, on February 5. The company said, consumer feedback has been taken into consideration to provide higher-quality images and more powerful creative control to the users. Gemini 2.5 Flash Image is priced at $30.00 per 1 million output tokens with each image being 1290 output tokens ($0.039 per image).

The Mysterious Nano-Banana Image Model is From Google and It's Rolling Out in Gemini

Google has already integrated it into Gemini, letting users edit and transform images with text prompts with impeccable accuracy over multiple generations. For weeks, the mysterious nano-banana image model has been earning praise for generating impeccably accurate images. It could realistically blend images, edit parts of images while maintaining incredible coherence, and transform photos with simple natural language prompts. As it turns out, the nano-banana image model is actually Google's Gemini 2.5 Flash Image AI model. Yes, you read that right. Google was the first company to showcase Gemini's native image generation in March and it was powered by the Gemini 2.0 Flash Image model. Now, the upgraded native image generation feature is powered by Gemini 2.5 Flash Image. Unlike Diffusion models, it's natively multimodal and maintains incredible accuracy over multiple generations. The new Gemini 2.5 Flash Image (nano-banana) is currently the top-rated model on LMArena for image editing. It has scored a whopping 1,362 ELO points, much higher than the second best, Flux.1 Kontext [max] which has received 1,191 points. It goes on to show that Google's Gemini 2.5 Flash Image model is top-notch and can edit images conversationally while preserving the scene. What is interesting is that Google is already integrating the new image model in Gemini. Starting today, you can upload and edit images in Gemini and it will use the new Gemini 2.5 Flash Image (nano-banana) model. You can use this feature to combine multiple images, change specific parts of the image using text prompts, reimagine yourself in different avatars, and more. You can even try new costume, change the location, mix up images, and perform multi-turn editing over and over again while preserving the overall scene. Note that all images generated in the Gemini app will have a visible 'ai' watermark and an invisible SynthID watermark.

Gemini 2.5 Flash image generation and editing model launched

Google unveiled Gemini 2.5 Flash Image (aka nano-banana), the company's latest image generation and editing model. The model is designed to excel at maintaining character consistency, adhering to visual templates, enabling targeted transformations, and making precise local edits using natural language. This latest image generation and editing model tops the LMArena's Image Edit Arena leaderboard, outperforming FLUX.1 Kontext model in terms of voting and score. For wider availability, Google has integrated it into its Gemini app, allowing users to create their perfect picture. Demonstrating various use cases of the model, Google has listed certain capabilities for users to try out: It is also available via the Gemini API and Google AI Studio for developers and Vertex AI for enterprise. Gemini 2.5 Flash Image is priced at USD 30.00 per 1 million output tokens, with each image being 1290 output tokens (USD 0.039 per image).