Google's 'Nano Bananas' AI Image Editor: A Viral Sensation with Mixed Results

I Tried Gemini's 'Nano Bananas' for Image Editing. The AI Slipups Were Obvious

After seeing all the banana-fanfare for Google's newest generative AI tool, I knew I had to take it for a spin. Named Gemini 2.5 Flash Image, the model upgrades your ability to edit your photos natively in Gemini. AI enthusiasts have referred to it as the "nano bananas" model, spurred on by a series of banana-themed teasers from Google execs. In the few weeks it's been out, people have created over 200 million AI images, and over 10 million people have signed up to use the Gemini app, according to Josh Woodward, Google's vice president of Google Labs and Gemini. Google has invested 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 AI giants. And creators have made more than 100 million AI videos with Google's AI filmmaker tool, Flow. I've spent a lot of time testing AI creative software, and I was excited to see what Google had cooked up. But my testing of 2.5 Flash Image showed that just because something has a flashy entrance doesn't mean it'll always lives up to its hype. Here's how my experience with Gemini nano bananas went: the good, the bad and the frustrating. The Gemini bananas model is spookily good at adding elements to existing images, blending AI-generated elements well into any picture you snapped. It also maintains a decently stable level of character consistency -- meaning the people in my photos weren't too distorted or wonky after going through the AI processing. Those are both important distinctions for AI image programs, and something Google said it had worked to improve. You can see both of these characteristics in this picture of my sister and me. Our general appearances are unchanged in the edited version (right), showing off that character consistency. I asked Gemini to add a third sister who looked similar to the two of us, which it did scarily well by adding a third woman in between the two of us. I was also pretty impressed with how quickly Gemini could spit out completed images. Anywhere under a minute gets a gold star from me, and Gemini was regularly handling requests in under 15 seconds. I also appreciated how it added a watermark to all the images it created and edited -- even if I don't love how tech companies have corrupted the sparkles emoji for AI, it's extremely important to have some markers of AI-generated content. Google's SynthID and behind-the-scenes work also help differentiate AI content from human-created imagery. Gemini is good at wholesale AI image creation, too, but I recommend using its Imagen 4 or another AI image generator instead -- they have more hands-on controls and settings that get you closer to what you want with less work. There are serious limitations to Gemini bananas. It automatically generated square images, and follow-up prompts asking for images to be adapted into other dimensions were ignored or failed. I also noticed that Gemini reduced the resolution of many of my photos. I primarily take photos with my iPhone 16, which has stellar cameras, but after going through the Gemini bananas model, those fine details were often blurred. That's annoying and won't win over any photographers. I tried repeatedly to get Gemini to handle photo edits that would've been difficult for me to do manually. That's one area in photo editing where AI is supposed to excel -- automating mundane but detail-intensive edits. Sadly, Gemini really struggled with prompt adherence here, meaning it didn't do what I asked. I tried many times to get Gemini to remove reflections from a snap of a Freakier Friday movie poster, but they stubbornly remained. And the more I tried to get it to remove the reflections, the poorer the quality of the image became with every prompt. Once-clear text was ultimately illegible after I finally gave up, not to mention the accidental, scary-looking damage done to the faces of Lindsey Lohan and Jamie Lee Curtis. Gemini nano bananas struggled to generate images in different dimensions. Resizing and cropping images is a core photo editing process, but Gemini didn't -- or couldn't -- handle simple sizing guidelines in my prompts. I reached out to Google about the resolution and dimension issues and a spokesperson said the tech company is "aware and actively working on both issues. It's been a big update from our previous model but we'll continue to improve on the model." Overall, Gemini nano bananas proved to me that Google is serious about continuing to dominate in generative media. But it has significant pitfalls, with too big a focus on generating new elements rather than using AI to improve and tweak common photo issues. For now, the nano bananas model is best suited for Gemini fans who want to make big edits quickly. For those of us looking for more precise tools, we'll have to wait for Google's next big update or find another program. You don't need to do anything to access the new model; it's automatically added to the base Gemini 2.5 Flash model. Gemini is available for free, with more models and higher usage caps available in Google's AI plans starting at $20 per month. If you're a paying subscriber, you may also be able to access the model through Google AI Studio. From there, all you have to do is upload an image and type out your prompt. Each prompt uses anywhere from one to two thousand tokens, depending on the level of detail required. Adobe Express and Firefly users can also access the new model now. 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.

Gemini's 'Nano Bananas' AI Image Editing Is Fun, but I Ran Into Too Many Slipups

I've been trying out the image editing capabilities in Google's latest generative AI model, and you can, too. Named Gemini 2.5 Flash Image, it upgrades the ability to edit your photos natively in Gemini. AI enthusiasts have referred to it as the "nano bananas" model, spurred on by a series of teasers from Google execs. 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 AI giants. And creators have made more than 100 million AI videos with Google's AI filmmaker tool, Flow. I've spent a lot of time testing AI creative software, and I was excited to see Google's latest drop amid all the banana fanfare. But my testing of 2.5 Flash Image showed that just because something has a flashy entrance doesn't mean it'll always lives up to its hype. Here's how my experience with Gemini nano bananas went: the good, the bad and the frustrating. The Gemini bananas model is spookily good at adding elements to existing images, blending AI-generated elements well into any picture you snapped. It also maintains a decently stable level of character consistency -- meaning the people in my photos weren't too distorted or wonky after going through the AI processing. Those are both important distinctions for AI image programs, and something Google said it had worked to improve. You can see both of these characteristics in this picture of my sister and me. Our general appearances are unchanged in the edited version (right), showing off that character consistency. I asked Gemini to add a third sister who looked similar to the two of us, which it did scarily well by adding a third woman in between the two of us. I was also pretty impressed with how quickly Gemini could spit out completed images. Anywhere under a minute gets a gold star from me, and Gemini was regularly handling requests in under 15 seconds. I also appreciated how it added a watermark to all the images it created and edited -- even if I don't love how tech companies have corrupted the sparkles emoji for AI, it's extremely important to have some markers of AI-generated content. Google's SynthID and behind-the-scenes work also help differentiate AI content from human-created imagery. Gemini is good at wholesale AI image creation, too, but I recommend using its Imagen 4 or another AI image generator instead -- they have more hands-on controls and settings that get you closer to what you want with less work. There are serious limitations to Gemini bananas. It automatically generated square images, and follow-up prompts asking for images to be adapted into other dimensions were ignored or failed. I also noticed that Gemini reduced the resolution of many of my photos. I primarily take photos with my iPhone 16, which has stellar cameras, but after going through the Gemini bananas model, those fine details were often blurred. That's annoying and won't win over any photographers. I tried repeatedly to get Gemini to handle photo edits that would've been difficult for me to do manually. That's one area in photo editing where AI is supposed to excel -- automating mundane but detail-intensive edits. Sadly, Gemini really struggled with prompt adherence here, meaning it didn't do what I asked. I tried many times to get Gemini to remove reflections from a snap of a Freakier Friday movie poster, but they stubbornly remained. And the more I tried to get it to remove the reflections, the poorer the quality of the image became with every prompt. Once-clear text was ultimately illegible after I finally gave up, not to mention the accidental, scary-looking damage done to the faces of Lindsey Lohan and Jamie Lee Curtis. Gemini nano bananas struggled to generate images in different dimensions. Resizing and cropping images is a core photo editing process, but Gemini didn't -- or couldn't -- handle simple sizing guidelines in my prompts. I reached out to Google about the resolution and dimension issues and a spokesperson said the tech company is "aware and actively working on both issues. It's been a big update from our previous model but we'll continue to improve on the model." Overall, Gemini nano bananas proved to me that Google is serious about continuing to dominate in generative media. But it has significant pitfalls, with too big a focus on generating new elements rather than using AI to improve and tweak common photo issues. For now, the nano bananas model is best suited for Gemini fans who want to make big edits quickly. For those of us looking for more precise tools, we'll have to wait for Google's next big update or find another program. You don't need to do anything to access the new model; it's automatically added to the base Gemini 2.5 Flash model. Gemini is available for free, with more models and higher usage caps available in Google's AI plans starting at $20 per month. If you're a paying subscriber, you may also be able to access the model through Google AI Studio. From there, all you have to do is upload an image and type out your prompt. Each prompt uses anywhere from one to two thousand tokens, depending on the level of detail required. Adobe Express and Firefly users can also access the new model now. 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.

Nano Banana brings in 10 million new Gemini users

Google's experimental Gemini 2.0 Advanced model is here, but not for everyone Google's latest AI experiment just graduated from inside joke to mass phenomenon. The model that leaked under the name Nano Banana has been officially live in the Gemini app as Gemini 2.5 Flash Image for just over a week -- and the numbers show just how quickly it's taken off. Silly name, powerful tool Let's be honest: Nano Banana > Flash Image In a post on X, Josh Woodward, VP of Google Labs, revealed that more than 200 million images have already been edited with the tool, with over 10 million people trying Gemini for the first time since its release. That kind of growth is rare even by Google's standards. Woodward's post summed up the scale excitedly: "TPUs red hot, SRE pagers howling." The hype didn't come out of nowhere. For weeks, Nano Banana had been circulating online as the mysterious editor that somehow avoided the uncanny valley problem plaguing other AI image apps. Where competitors stumble on repeated tweaks, running into trouble like warped faces or decreasing likeness, Nano Banana nails consistency. You can repaint your living room three times over, stick your chihuahua in a tutu, or swap yourself into a matador costume, and the model still keeps you recognizably you. That "stickiness of self" is what turned a silly code name into a viral sensation, topping LMArena's editing benchmarks before Google even admitted ownership. Now that it's rebranded as Gemini 2.5 Flash Image, Google is positioning it as a clear differentiator in the crowded AI editing market. Access is tiered: free Gemini users get 100 edits per day, while paying subscribers can push to 1,000 edits. Every output carries Google's SynthID watermarking, visible and invisible, to flag AI content. The simple strategy paid off. Hook people with a model that feels like magic, then pull them deeper into Gemini. And so far, it's working. Most AI editors make for cool demos, but Nano Banana has crossed into real usability. As we're starting to see, Google didn't just ship another toy. With Gemini 2.5 Flash Image, it may have found the rare AI feature that people actually want to use every day.

Nano Banana responsible for 10+ million first-time Gemini app users

Following last week's announcement, Google shared today how much of a hit Nano Banana has been for the Gemini app. Officially, it's called Gemini 2.5 Flash Image, but Google is actively referring to it as Nano Banana in various places. That codename from the testing process really struck, with a banana emoji now present in the Gemini prompt bar. It's also "Nano Banana" in AI Studio and there's even a @NanoBanana social account. On LMArena's Image Edit leaderboard, it's #1 by a wide 171-point margin. This image editing model's main advancement is how it maintains character likeness and consistency. There's also the ability to upload multiple photos, style transfer, and multi-turn/prompt editing. Google's Josh Woodward shared today that over 200 million images have been edited since the launch last Tuesday. Even more notable is how over 10 million people using Nano Banana are new to the Gemini app. The buzz around this native image editing has driven app downloads, with Google Gemini currently #2 in the Productivity category of the App Store. In the Play Store, it's #13 of the main top free chart. In other model news, Google Photos is now rolling out Veo 3 for photo to video for "even higher-quality clips." It originally launched with Veo 2 in July. This is available for all users, though subscribers can generate more.

Nano Banana just broke the internet with these viral trends -- here are 5 AI photo prompts to try now

Within just a few days of launching, Google's VP, Josh Woodward posted on X that the Gemini app has over 10 million new users thanks to Nano Banana. If you've tried it, than you already know why users from all over the world are flocking to Google's new AI image generation and editing tool. Built directly into Gemini, this ultra-fast model focuses on visuals at much higher speeds than ChatGPT or even MidJourney. Baked right into the Gemini ecosystem, 200 million images have already been generated or edited, and it has spurred a number of viral trends that I just couldn't wait to try. Here's what happened when I tried them, as well as the prompts you can use to try them for yourself. Prompt: "Take this photo of me and turn me into a collectible figurine inside a toy box. The box should include a clear window to show the figurine, bold graphics, and my name on the packaging. Style the figurine in a fun, toy-like way but keep my likeness recognizable. Make it look like an authentic action figure you'd find on a store shelf." Similar to the ChatGPT-4o trend, Gemini takes the trend to the next level by generating a better image that better resembles the user, faster. Prompt: "Take this photo of me and transform me into a 1980s character, with big hair, neon clothes, and a retro mall arcade in the background. Update my clothing, hairstyle, and background to match the era. Make it look like an authentic portrait from that decade, with accurate fashion, colors, and overall style." Try other decades by using these additions to the prompt: 1920s: "Transform me into the 1920s, styled like a flapper-era portrait with vintage sepia tones, short bob haircut, and art deco patterns in the background." 1950s: "Show me in the 1950s, wearing retro diner-style fashion with a poodle skirt and leather jacket vibe, placed in front of a neon jukebox." 1970s: "Turn me into a 1970s disco look, complete with bell-bottoms, platform shoes, and colorful light patterns." 1980s: "Make me look like an 80s character, with big hair, neon clothes, and a retro mall arcade in the background." 1990s: "Reimagine me in the 90s, dressed in grunge or sitcom fashion, standing in a Blockbuster video store." Take yourself 'back to the future' by placing yourself in different decades. This one is a lot of fun, especially if you try a variety of decades. Pro tip: ask Gemini to generate several decades all at once so you can see them all side-by-side. Prompt: "Create a realistic image of me sitting with Jerry, Elaine, George, and Kramer in Jerry's apartment from the TV show Seinfeld. I'm part of the group, sitting on the couch with them, laughing as if I just delivered a punchline. Make sure the scene looks like a classic episode, with Jerry's kitchen in the background and the group's casual 90s outfits. Include me seamlessly in the style of the show." One thing I've noticed after testing hundreds of Nano Banana prompts is that if you want the best possible outcome, upload a picture of you doing what you want to be doing in the Nano Banana scene. For example, upload yourself sitting if you want to be sitting. Prompt: "Take this photo of me and insert me into Edvard Munch's The Scream. Paint me in the same expressionist style, with bold swirling colors and dramatic brushstrokes. Place me standing on the bridge alongside the central screaming figure, blending seamlessly into the eerie, emotional atmosphere of the painting." More prompt examples to try: Mona Lisa (Leonardo da Vinci): "Insert me into Leonardo da Vinci's Mona Lisa. Place me next to the original subject, painted in the same Renaissance style with soft lighting and muted colors." Starry Night (Vincent van Gogh): "Place me into Vincent van Gogh's Starry Night, painted in the same swirling brushstroke style, standing beneath the starry sky in harmony with the scene." The Persistence of Memory (Salvador Dalí): "Add me to Dalí's The Persistence of Memory. Show me in surreal form, painted with melting features and dreamlike colors to match the surrealist style." American Gothic (Grant Wood): "Put me into Grant Wood's American Gothic, holding a pitchfork beside the farmer and painted in the same realistic 1930s style." I had to try this a few times because the image didn't always come out. As in, not at all. When I asked for the Mona Lisa, all I got was two Mona Lisa images side-by-side. Out of all the prompts, this one was probably the hardest. If you try this one, let me know your thoughts in the comments. Prompt: "Take this photo of me put me sitting on top of the Hollywood Sign, waving at the city below.. Make it look realistic, with accurate lighting, shadows, and perspective so it feels like I'm actually there. Keep the landmark clear and recognizable and match the overall atmosphere of the location." More prompt examples to try: Eiffel Tower (Paris): "Put me in front of the Eiffel Tower on a sunny afternoon, dressed casually, with tourists and city life around me." Great Wall of China: "Place me walking along the Great Wall of China, with the winding wall stretching into the mountains behind me." Taj Mahal (India): "Insert me into the gardens in front of the Taj Mahal at sunrise, with the monument reflecting in the water." Statue of Liberty (New York): "Show me standing near the Statue of Liberty, with the New York skyline in the background and bright daylight for realism." Pyramids of Giza (Egypt): "Place me next to the Pyramids of Giza, with desert sand and camels nearby, blending naturally into the historic scene." For the second one, I had a little extra fun and asked Gemini to combine two pictures. One of me and one of Harry Styles using the prompt: "Combine these two photos and place the people together in the same scene. Make it look natural and realistic, with consistent lighting, shadows, and background. Position them so they appear to be hanging out casually, smiling and interacting as if the photo was taken in one moment." This was my favorite prompt, naturally. Nano Banana is a blast and easily one of my favorite image generators. It's fast, mostly accurate and does more than other image generators I've tested. It's shaping trends as more users discover how easy it is to create images with a single prompt. The best way to understand its appeal is to try it yourself, experiment with prompts and see how far you can push its creativity. Just remember, it's not always perfect. Sometimes the results are a little off, and it may take a few tries with new photos or extra prompting to get exactly what you want. But if you ask me, that trial-and-error is part of the fun.

I turned myself into a 3D figurine with Google's Nano Banana - here's how you can hop on the latest AI image trend

Google's latest image model, Gemini 2.5 Flash Image, also known as Nano Banana, has produced a fun new trend using its advanced image capabilities. You can turn yourself (or your pet) into a highly detailed 3D figurine. All you need to do is upload a photo and employ a very detailed prompt to have a stylized image of a miniature, plasticized version of the subject, posed on a little clear base, less than a minute later, with a box and even a wire-frame model to show it off. This particular flavor of AI-generated toy is exploding across social media right now because the model is fast, free, and surprisingly good at what it does. Unlike earlier versions of these kinds of prompts that ran on GPT-4o or Midjourney, Nano Banana has better prompt adherence, understands packaging and posing more consistently, and renders faces that, while not always perfect, are often impressively accurate. It's all built into Google AI Studio and the Gemini apps and website if you want to try it. You just have to upload a picture, ideally a full-body shot, of who or whatever you want to make into a figurine, and submit the right prompt. You can play around with it, but the following template, shared around on social media, works very well. Type this in: "Create a 1/7 scale commercialized figurine of the characters in the picture, in a realistic style, in a real environment. The figurine is placed on a computer desk. The figurine has a round transparent acrylic base, with no text on the base. The content on the computer screen is a 3D modeling process of this figurine. Next to the computer screen is a toy packaging box, designed in a style reminiscent of high-quality collectible figures, printed with original artwork. The packaging features two-dimensional flat illustrations." When you paste that into Gemini, along with a photo, it doesn't just try to render a toy version of what's in the picture, it imagines the toy existing in the real world, with all the context that goes along with a premium 3D figurine release. It's like a high-end collectible a company would make if you became famous for whatever pose you you're in. I went with fun photo of myself from a big circus-themed party a few years ago where I went as a lion tamer (see the small lion in my pocket). I shared the photo with Nano Banana along with the prompt and twenty seconds later, there "I" was, six inches tall, standing on a desk and looking jaunty with my whip like I was about to command a herd of miniature jungle cats. The packaging beside me showed a great illustrated version of the same pose, except it decided I was the ringmaster and named Rhett for some reason. The computer screen behind the figurine showed a 3D modeling window open with "my" miniature wire-frame form on it, being rotated in space like it was being finalized for mass production. It genuinely looks like a photo, right down to the scuffed desk and random paperwork. Even the stuffed lion in my pocket looked right. It felt like an alternate version of me had been shrink-wrapped and made collectible. Next, I decided to try with a photo of my dog, Cabbage. I uploaded a picture of her sitting regally on the ground and used the same default prompt. The toy created by the AI was almost too realistic. I had to look closely to tell it's supposed to be made of molded plastic. The screen behind the figure showed the hound rendered in a 3D modeling program appropriately, but the packaging went a little awry. It had multiple images of the dog like it was a test of different poses. But I did like that, lacking her real name, the AI went with her bandanna to name her Firecracker Fido. The thing that struck me after both generations was how smoothly it all worked. No fine-tuning needed to get 95% of the way there. The Nano Banana just understood the visual reference and ran with it. I wouldn't claim it's anything like as valuable as what real human artists can do, but it was a fun experiment. Much like the Studio Ghibli AI image trend, it's worthwhile for personal amusement, but the idea of using these images for any kind of money-making scheme to sell actual toys would be several steps beyond propriety.

Google Can Turn Your Photos into a Toy Action Figure

Google recently introduced a powerful new AI model that can edit photos as well as generate synthetic images. And now a viral trend sees people turning theirphotos into imaginary figurines. Google's Nano Banana model, officially known as Gemini 2.5 Flash Image, has got its first fad. Although turning photos into action figures isn't exactly new since people made similar images with ChatGPT earlier this year. Nano Banana can be found on Google's Gemini app, which officially acknowledged the trend in a post on X. It also provided the prompt for people to have a go themselves. There is a Gemini app, or simply head to the Gemini website. Upload the photo you want to use and then type in the following prompt. The prompt, of course, can be tweaked. 'Create a 1/7 scale commercialized figurine of the characters in the picture, in a realistic style, in a real environment. The figurine is placed on a computer desk. The figurine has a round transparent acrylic base, with no text on the base. The content on the computer screen is a 3D modeling process of this figurine. Next to the computer screen is a toy packaging box, designed in a style reminiscent of high-quality collectible figures, printed with original artwork. The packaging features two-dimensional flat illustrations.' Not wanting to miss out, I had a go myself. The trick to this is picking the right photo. As photographers, we should have quality, well-lit, high-resolution photos to choose from, which most definitely helps. A full-length picture of the desired subject also helps.

How to Use Google's Nano Banana AI to Transform Your Selfies Into Digital Figurines - Decrypt

Politicians and influencers are adopting the trend, while advanced users tweak materials, poses, and props for personalized dolls. Google's latest AI model has sparked another viral transformation trend, with millions of users turning themselves into miniature Bandai-style figurines that look pulled from a Tokyo toy store shelf. The tool, nicknamed Nano Banana after its internal codename at Google DeepMind, officially launched as Gemini 2.5 Flash Image in late August. Within two weeks, users generated over 200 million images. The Philippines alone accounts for 25.5 million image creations just days after its launch, making it the top region globally for use. "From photo to figurine style in just one prompt," Google's Gemini team posted on X September 1, kicking off tutorials that spread the trend further. Josh Woodward, Google's VP, reported 10 million new Gemini users joined specifically for the feature. The digital figurines appear as 1/7 scale collectibles on clear acrylic bases, often displayed next to packaging boxes and computer screens showing 3D modeling software. The AI captures facial features, clothing details, and poses with enough accuracy that results frequently fool viewers into thinking they're real product photos. This marks the third major AI portrait trend of 2025. ChatGPT's GPT-4o sparked the Studio Ghibli wave in March, with users transforming photos into soft, anime-style portraits reminiscent of Hayao Miyazaki's films. Sam Altman changed his X profile picture to a "Ghiblified" version of himself as servers struggled under "biblical demand." April brought the Barbie Box Challenge through ChatGPT, where people became plastic dolls in blister packaging, complete with accessories like tiny laptops and coffee mugs. LinkedIn professionals embraced it for personal branding, turning themselves into "executive action figures." Nano Banana isn't the only player in this space. Alibaba's Seedream4, released just a few days after Google's model, produces outputs with comparable quality and sometimes better consistency in complex poses. For those preferring open-source alternatives, Flux Kontext offers the most powerful option for local deployment. It integrates into complex workflows and remains the only model without content restrictions, though that flexibility comes with the usual responsibilities of self-hosted AI. Creating your own Nano Banana figurine takes under a minute. Visit gemini.google.com or open the Gemini app -- the basic version is completely free, though your daily generations are limited. Click on the option to try Nano Banana, which you can find it in the banner on top. It is also under "tools" as "Create Images." (Google is showing banana emojis everywhere, so you won't have any trouble finding it.) Next, upload your photo or the photo of the person you want to turn into a doll, preferably a full-body photo with good lighting. You can do that by clicking on the "Plus" button next to "tools." We trust you will be responsible, ok? Once the image has been uploaded, paste in this prompt: "Create a 1/7 scale commercialized figurine of the character in the picture, in a realistic style, in a real environment. The figurine is placed on a computer desk. The figurine has a round transparent acrylic base, with no text on the base. The content on the computer screen is a 3D modeling process of this figurine. Next to the computer screen is a toy packaging box, designed in a style reminiscent of high-quality collectible figures, printed with original artwork." There are some tweaks you can make to customize your doll. Specifying materials like "PVC figure" or "polished resin" increases realism. Dynamic poses work better than static standing positions -- arms outstretched or mid-action yield more convincing figures. If you don't think the model is realistic enough, adding something like "The face is exactly the same" or "the face remains unaltered," does the trick. But beware, you may end up with something too realistic and not really doll-like. Don't go too crazy, though. The free tier offers limited daily edits, while the pro version removes restrictions. Some platforms, like Freepik, give users unlimited iterations (and unlimited Wan 2.2 videos too) with the tradeoff of a small degradation in quality after a very generous threshold is met. Advanced users chain multiple prompts for complex scenes. After generating the base figurine, you can improve your doll with further iterations -- asking it, for example, to change the clothes, add props, alter the pose, etc. Nano Banana's outstanding character reference makes it a very powerful tool that won't degrade your face too much after many iterations. This is something that previous models used to struggle with. The figurine aesthetic has proven particularly sticky on social media. Politicians in India and the Philippines posted their miniature versions, while TikTokers use the hashtag #NanoBanana to share increasingly elaborate scenes with multiple figures and custom dioramas.

Google's Nano Banana available on X: Here's how to use - The Economic Times

Google has launched Nano Banana, an AI image generation and editing tool, accessible on X. Users can create and modify images by tagging the AI and providing prompts. This tool, along with the Gemini 2.5 Flash Image upgrade, offers features like image blending, character consistency, and targeted transformations using natural language. Gemini 2.Google's latest artificial intelligence (AI) based image generation and editing model, Nano Banana, is available for users on X, formerly Twitter. Tagging the AI tool on X and adding the prompt will generate the desired images. A post on the official Nano Banana X handle read: "Try the Gemini App or tag me Nano Banana to generate/edit an image." Google had unveiled Nano Banana along with the Gemini 2.5 Flash Image upgrade. Nano Banana features The AI tool allows users to: Gemini 2.5 Flash Image The update became available late in August 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. Google had 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 per 1 million output tokens, with each image being 1,290 output tokens ($0.039 per image).

The New Google AI Tool That Has Everyone "Going Bananas" is Now on X

With this launch, Google is seeing wider adoption of Gemini and so far, 10 million new users have joined in. Google's Nano Banana AI image model that surprised users with its highly consistent photo editing is now available on X (formerly Twitter). You can now tag @NanoBanana on X and ask it to generate an image or edit a photo with a custom prompt. While Google rolled out Nano Banana on the Gemini app for free, the company has also brought the viral image model to X. Along with Grok and Perplexity, now you have Google's Nano Banana model on X to generate and edit images on the go. You can even tag it in replies or new posts to produce images. Not to mention, you can upload multiple images on X and tag @NanoBanana to combine these images. Google's AI model is amazing at maintaining the characters consistent across multiple generations. Here are some of the images created by @NanoBanana on X. The AI model is very good at creating infographics as well. Note that Nano Banana is a playful name for the Gemini 2.5 Flash Image model. It currently tops the LMArena image leaderboard for image editing and generation with a substantial lead. Josh Woodward, who leads the Gemini app at Google, shared on X that following the release of the Nano Banana image model, over 200 million images have been edited. On top of that, more than 10 million new users have joined the Gemini app. So, what are you waiting for? Go ahead and tag @NanoBanana on X to generate and edit images for free. You no longer have to learn Photoshop to edit and make finer adjustments to images. AI Image editing is now just a natural language prompt away.

Here's how people are making those viral 3D figurines

It seems each major new AI image generator sparks a new viral trend that takes over the internet for a few days. With the launch of GPT‑4o back in March, it was Studio Ghibli-style images. Now with Google's Nano Banana, AKA Gemini 2.5 Flash Image, it's 3D figurines. It isn't an entirely new trend. People had already displayed a penchant for creating action figures of themselves using GPT-4o. But Nano Banana appears to be capable of more detail and more sophisticated prompt adherence. Sometimes they're cute, and sometimes they're more than a little creepy. People have also discovered that they can turn static images of their 3D figurines into videos. It's at times like this that I realise how few photos I have of myself - particularly full-length ones. The only one I could find was a relatively low-resolution photo taken in quite harsh conditions, so Nano Banana didn't have great data to work with, but the model still managed to identify the subject of the photo, complete with mate and tripod, and turn it into a 3D figure. With a better quality image, you're likely to get more detail and a more realistic likeness. You can also add instructions to the prompt to specify if you want the figurine to be in a different pose. You can also specify any text you want to appear on the packaging and it does a fairly decent job at apply that instead of the usual AI garbled text. As with all AI image generators, results can be inconsistent. You can animate your AI-generated image using any number of AI video generators that are coming out. Prefer to get more creative and do it an old-school way? Don't miss the optical illusion of the year competition entry that ingeniously recreated the AI figurine trend for real. For more AI news, don't miss the story of OpenAI's big bet on AI filmmaking with its AI animation Critterz.

How to turn your selfies into action-figure style 3D models with Google AI: Step-by-step guide

Users can customise prompts for personalized figurine designs. If your Instagram feed is full of people flexing miniature 3D versions of themselves or their pets, it's possible that they've used Google's most recent Gemini update. The tool, also known as the Nano Banana, is powered by Google's Gemini 2.25 Flash Image model and can instantly transform any uploaded photo into a lifelike 3D collectable figurine. The new feature has gained popularity online because it is simple to use, does not require any professional skills, and can be completed using a single text prompt, all for free. All you need is a Google account, which you can get for free through Google AI Studio. After that, upload the image, and the AI will convert it into a 3D render in a matter of seconds. Are you wondering how? Here's a step-by-step guide. Also read: Apple iPhone 16 Pro and iPhone 16 Pro Max get massive price cut after iPhone 17 series launch All users are advised to tweak the prompts to get a more personalised response.