Tag:

Nano

Wall of video screens with an AI video generation button.
Gaming Gear

How to Use Google’s ‘Nano Banana’ AI Photo Editor: My Expert Tips

by admin


Google’s new AI image model got the nickname “nano banana” after a series of fruit-themed teasers from its executives and early reviewers thought its capabilities were, well, bananas. Since its launch, the nickname “nano banana” has stuck. But don’t worry if you’re not sure exactly what that’s referring to. Here’s what you need to know to find the model and make the most out of this powerful new tool.

The model’s government name is Gemini 2.5 Flash Image — it doesn’t sound nearly as fun as “nano banana,” but it’s important to note. It’s taken off dramatically in the past few weeks, especially compared to other AI image tools. Google reported that its users made over 5 billion AI images, and the model led to over 10 million new Gemini users in the first few weeks after nano banana’s release. It also helped launch Gemini to the top of the Apple App Store’s free app chart for a while. 

Although Google’s invested in integrating AI everywhere, nano banana image editing seems to be making one of the biggest leaps for Google in the race to develop the best AI.

As CNET’s AI image generator expert, I put nano banana to the test to see if the model held up or if it was all simply AI hype. I found Google’s nano banana impressive, with its refreshing focus on editing existing photos. There were still some slipups, which is to be expected with any AI service. But it was spookily good at adding new elements to my existing photos. If you’re an AI enthusiast, or even someone who just needs a quick, custom photo edit, I do think it’s worth exploring. 

To save you time, this guide is built on my real experience finding and playing with the model, along with some crowd-sourced tips for the best results. For more, check out our guides on creating AI images and writing the best AI image prompt.

How to access Google’s nano banana

You can access nano banana in a couple of ways. If you want to go directly through Google, you’ll need to have Google’s AI Pro plan, an AI-specific subscription that’s $20 a month. Once you’re signed up, you can navigate to Google’s AI Studio and select 2.5 Flash Image as the model you want to use. You can’t edit photos with it through your Gemini chats, unlike with OpenAI’s image generation with ChatGPT.

Developers can also access the model through Vertex AI and the Gemini API. If you don’t know what those are, you probably don’t have access to them. So don’t worry about it and stick with the AI Studio, which is open to everyone.

You can also use nano banana through certain Adobe programs. Nano banana is available as a third-party model in Photoshop, Adobe Express and on its AI platform, Firefly. Those programs are also usually paywalled, but it’s worth checking to see if you have access to them if you use some Adobe programs already. Make sure you select 2.5 Flash Image before you click generate, as Adobe has many third-party models available.

As always, an important note about privacy: Google’s general 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. And nano banana-edited photos aren’t watermarked, so be sure to disclose that you used AI when sharing those images.

Don’t miss any of our unbiased tech content and lab-based reviews. Add CNET as a preferred Google source.

How to use Google’s nano banana and get the most out of it

Once you’re in Google’s AI Studio, you can easily upload your image for editing. But like any AI image tool, your chances of success depend on how well you prompt the model. Here are some tips for using nano banana.

  • Be specific. Writing an AI prompt is different from doing a Google search. The more details you provide, the more likely it is you’ll get the result you want. Talk about the colors, the style, the aesthetic. Keywords are great, but don’t worry about writing too much.
  • Tell it what you don’t want changed. This is different from the advice I give when dealing with AI image generators. Most AIs struggle to understand negative prompts, or things you don’t want to see. But nano banana is decent at understanding what you do and don’t want adjusted, so include that in your prompts.
  • If you want text, tell it exactly what words you want. I admit, this is partially inspired by Google’s own best practices for prompting, but it’s also something I’ve seen in my own testing. You need to be specific when you want text; otherwise, it will end up messy. Don’t forget to include the style and color of the font, too.

An example of how I edited an existing photo (left) with nano banana to include a new element — a spookily similar looking sister in the AI-edited photo (right).

Katelyn Chedraoui/CNET

One of the best things you can use nano banana for is adding new elements to an image you already have. But there are some other good use cases. Here are some ideas to help spark your inspiration, based on some of my favorite prompts I use to test AI services.

  • Play around with variations. You can ask the model to create different versions of your existing photo, whether that’s a headshot with different hairstyles or transform your photo into a different style. I’ve taken nature landscapes I photographed and had AI reimagine them in the style of a dark, sci-fi or fantasy world, for example.
  • Use nano banana as an AI-powered eraser. Removing background distractions is one of the most common uses of photo editing software. Any AI worth its weight should be able to help you get rid of errant obstructions and blend the affected area seamlessly into your photo.
  • Ask Gemini for inspiration or ideas when you’re stuck. I always recommend talking through photo editing projects with real people when you’re able. But when you’re not able to, you can use the chatbot as a kind of sounding board for your ideas. Gemini can also help you put your own ideas into words that nano banana will be able to understand.

For more, check out my full hands-on experience with Google’s nano banana and the best AI image generators.



Source link

0 comments
0 FacebookTwitterPinterestEmail
A female photographer holding the DJI osmo Nano
Product Reviews

DJI Osmo Nano review: a tiny modular action cam big that’s big on quality

by admin



Why you can trust TechRadar


We spend hours testing every product or service we review, so you can be sure you’re buying the best. Find out more about how we test.

DJI Osmo Nano: two-minute review

The DJI Osmo Nano is the latest in the brand’s line of action cameras. Rather than building on a predecessor it’s a whole new concept in its own right, although it shares the same-sized 1/1.3-inch CMOS sensor as the DJI Osmo Action 5 Pro, which landed at the end of 2024.

The range of best action cameras is more diverse today than it was even just a few years ago. The one-block shops of design like the GoPro Hero 13 Black are still popular, for sensible reasons like ruggedness and extended battery times, but modular designs like the Osmo Nano and the new Insta360 Go Ultra are becoming more common.

Why? We don’t just want to hold our action cams or use a fiddly mount to attach them to our bike handlebars anymore. The content creation universe is continuing to grow, and so is the number and variety of places where we need our cameras to go.

In a nutshell, the Osmo Nano is a light, wearable action camera. You can wear it around your neck, on your head, on a hat or helmet, plonk it on your car, bike, or even attach it to your dog. It’s remarkably small, and at 52g it’s a gram lighter than its main competitor, the Insta360 Go Ultra, released a month before it.

The product is modular in design and built as a two-piece system, with a tiny, standalone camera unit that pairs with the Multifunctional Vision Dock underneath. The dock acts as a remote, screen, and charging station, with a small but bright 1.9-inch display to help you compose shots and adjust settings.

(Image credit: Lauren Scott)

These two parts join together via two clips and a strong magnetic system, and it’s this magnet that also allows the camera to snap onto DJI’s various accessories, for a wide range of hands-free, wearable mounting options.

Although the camera is a fully IPX8-rated unit that’s waterproof down to 10m, the dock is only IPX4-rated for splash resistance, which limits its use in heavy rain or near a body of water – a totally rugged design this is not.

Inside the camera is a 1/1.3-inch CMOS sensor, which captures a dynamic range of up to 13.5 stops according to DJI. I haven’t done any calculations with my test images on this, but I did find great levels of detail and color in bright sky highlights as well as darker, shadowy areas like tunnels. I was genuinely impressed by the level of detail and tone the camera could capture, particularly for a sensor this small (in full-frame terms).

For me, DJI has always been a brand for what I’d call ‘serious’ creators, and that’s something I’m pleased to see the brand has leaned into with the Osmo Nano. There aren’t any ‘fun’ filters or gimmicks in the menus. Instead, the settings are pared back to sensible and helpful options; voice controls and gestures to start recording all work very well to make hands-free shooting that much easier.

A big draw for professionals is the color performance. I was surprised to discover that the Osmo Nano can record in 10-bit color with D-Log M and HLG profiles – a pro-level feature that gives you more leeway for color grading in post-production, if you want to edit manually rather than relying on the automatic outputs from the DJI Mimo app. In 10-bit, I found videos were punchy but still well-balanced.

(Image credit: Lauren Scott)

Performance-wise, the Osmo Nano delivers exceptionally well in some areas but underwhelms in others. The promise of rapid file transfer holds up, with the 128GB version clocking transfer speeds of up to 600MB/s over a USB 3.1 connection. This is a huge time-saver.

Battery life, however, is a clear limitation. While DJI claims up to 90 minutes from the camera and 200 minutes with the dock, I found that shooting at 4K/60fps got me closer to just 60 minutes of continuous recording. On the upside, the dock’s ability to fast-charge the camera to 80% in about 20 minutes means you can be back to shooting in no time.

The RockSteady 3.0 and HorizonBalancing stabilization features work well for walking or light activity, and even when I tried recording star jumps and high-intensity workouts, the footage was stable in sports mode. Audio quality is good all-round too, and two built-in microphones capture immersive stereo sound, with decent but not brilliant wind reduction. Another plus for more advanced creators is the ability to pair the Nano with two mics separately, and you won’t need receivers if they’re from DJI.

While the image quality is good for a camera this small, it’s still bound by the limitations of its form factor. The fixed 143-degree ultra-wide field of view is great for first-person shots, but obviously lacks the versatility of a more zoomed-in lens. And while DJI’s SuperNight mode for low-light shooting is better than ever, it’s limited to 30fps and 8-bit color.

(Image credit: Lauren Scott)

Today’s best DJI Osmo Nano deals

The Osmo Nano is pricing is really aggressive, coming in much cheaper than the Insta360 Go Ultra and the GoPro Hero 13 Black – and that’s with built-in storage too, meaning you can start shooting straight out of the box.

It’s not necessarily the most charming camera I’ve tested, but it’s thoroughly dependable and sensible, and for that reason I found it growing on me, while the low price sweetens the deal. The DJI Mimo app is less intuitive than Insta360’s, and AI edits are a little less exciting, but it’s smart and stable, and puts a clear live feed with access to settings at your fingertips on your smartphone.

DJI isn’t marketing the Osmo Nano for family users, and it lacks some of the fun features of the Insta360 lineup, plus Toddler Titan mode for capturing kids. While charging is fairly speedy it doesn’t charge as quickly as its main competitor, the Insta360 Go Ultra, either, but the camera does last longer.

If you need a fully rugged and all-in-one device for more extreme sports or environments, the GoPro Hero 13 Black or the DJI Action 5 Pro might be a better choice. But this is a well-thought-out, truly wearable action camera for creators who want to experiment with unique perspectives, and need a B-camera for places their main camera can’t go, for a B-cam price.

(Image credit: Lauren Scott)

DJI Osmo Nano: specs

Swipe to scroll horizontallyDJI Osmo Nano specs

Sensor

1/1.3-inch CMOS

Max Resolution

35MP (6880 x 5160) photos
4K, 60fps footage

Weight

Camera: 2.54oz / 53g Vision dock: 3.8oz / 72g

Dimensions

Camera: 57 x 29 x 28mm
Vision Dock: 59 x 42 x 22mm

ISO Range

100–25600

Lens

FOV: 143 degrees
Aperture: f/2.8
Focus: 0.35m to ∞

Operating Time

Camera: 90 mins*
Camera + Multifunctional Vision Dock: 200 mins*

Connectivity

Bluetooth, Wi-Fi, USB-C 3.1

Storage

64GB/128GB built-in
microSD card, up to 1TB

Waterproofing

Camera: 33ft (10m)
Vision Dock: IPX4-Rated

DJI Osmo Nano: Price and availability

  • Launched worldwide on September 23 2025, except US
  • Osmo Nano Standard Combo (64GB) costs £239 / AU$529
  • Osmo Nano Standard Combo (128GB) costs £259 / AU$589

The DJI Osmo Nano was announced on August 23, 2025, and is now shipping from DJI’s online store and authorized retailers, including Amazon. It won’t be available officially in the United States at launch. A DJI Spokesperson told TechRadar that “DJI remains dedicated to the US market and is optimizing our strategy to best serve our customers amidst evolving local conditions.”

There are two standard combos to choose between, broken down by the internal storage capacity: the Osmo Nano Standard Combo at 64GB (£239 / AU$529) or 128GB (£259 / AU$589).

Each combo comes with the same content, including the Osmo Nano Camera, Multifunctional Vision Dock, Magnetic Hat Clip, Magnetic Lanyard, a protective case, USB-C cable (USB 3.1), and a Dual-Direction Magnetic Ball-Joint Adapter Mount. The protective case is more just a plastic sheath rather than substantial padded protection.

That price puts it way below the Insta360 Go Ultra Standard Combo ($449.99 / £369 / AU$759), which is more impressive given that you get built-in storage too. It’s also less than the GoPro Hero 13 Black (now available for around $359.99 / £315).

Image 1 of 4

(Image credit: Lauren Scott)(Image credit: Lauren Scott)(Image credit: Lauren Scott)(Image credit: Lauren Scott)

DJI Osmo Nano: Design

  • Standalone camera is waterproof, dock is splashproof
  • Magnetic base connects easily to mounts
  • The camera weighs 1.83oz / 52g

The DJI Osmo Nano camera is oblong-shaped, about half as wide as it is long. It sits comfortably between your thumb and forefinger in either portrait or landscape mode, but I didn’t find it as pocketable as the Insta360 Go Ultra because of its extra depth.

Without the dock, the Osmo is a light, wearable action camera at just 52g. Adding the dock, by way of two secure mounting clips and a magnetic, adds another 72g and turns the camera into a more complete action companion. It’s small, but I found the combo top-heavy on uneven surfaces, making low-level shots without a mount more difficult.

There’s just one built-in OLED HD touchscreen on the dock, rather than a screen at the front and back, or a flippable design like the Insta360 Go Ultra. This means you have to detach and remount the camera every time you want to go from shooting your environment to talking to the camera (if you want to see yourself, that is). Unlike the Go Ultra, which simply plops back into place with strong magnets, flipping the Osmo Nano around is a bit fiddly.

The design is gray and plastic, which is familiar territory for both DJI and action cams in general. The body is subtly textured though, meaning it’s easy to grab onto with cold, wet or sweaty hands. Ruggedness is key for an action camera, but only the wearable part of the Osmo Nano is waterproof. The camera is IPX8-rated for submersion up to 10 metres underwater.

The dock is only splash, rain and likely sweat resistant, and I wouldn’t fancy its chances in a heavy rain shower. This is a shame, because it limits potential usage and introduces a little caution to creativity when shooting. It’s also a far cry from DJI’s Action 5 Pro, which is verified down to 20m / 65ft.

(Image credit: Lauren Scott)

While the dock isn’t waterproof, you can use the whole product in temperatures of -20C to 45C (-4F to 113F), so you’re good for everything from winter sports to desert treks. A lens cover screws over the main lens, so if you damage or scratch it a replacement costs a fraction of buying a whole new unit.

The Osmo Nano has just two physical controls: there’s a big red record button on the top of the camera and another on one side of the dock. These also act as power switches, and they require some force to push down so that you’re not likely to press them accidentally. That’s it, other than a small flap that opens up on the other side of the dock to reveal the USB 3.1 port for charging and transferring files, plus the microSD slot, which takes up to a 1TB card.

Image 1 of 3

(Image credit: Lauren Scott)(Image credit: Lauren Scott)(Image credit: Lauren Scott)

I didn’t find the DJI Osmo Nano as enjoyable or easy to navigate as other action cameras I’ve tested. You swipe up to access video settings, down for the main menu, and left to change the shooting mode. To toggle Pro Mode on or off, you tap the slider icon on the right side of the screen.

It’s not rocket science, but at 1.96 inches the small screen means you need to be extra precise with your touch gestures to bring up menus and dial in settings. My partner – who has bigger hands and fingers than I – sometimes had to tap the screen a few times to activate settings.

The menus are mainly black and white with yellow accents, and I found this less eye-catching than the GoPro or Insta360 ecosystems, although that may be more a matter of personal preference. Some settings are also overlaid on the live picture and can be difficult to read. The camera doesn’t have the same detailed tutorials and guides that you get when you start using the Insta360 Go Ultra, although I’m sure DJI fans will have no trouble finding their way around.

Image 1 of 1

(Image credit: Lauren Scott)

DJI Osmo Nano: Performance and features

  • Quick-edit videos on the DJI Osmo Mimo app
  • Standalone camera charges 80% in about 20 mins
  • In-built storage and takes microSD cards up to 2TB

The performance of the Osmo Nano is hard to pin down. In some areas I felt it delivered exceptionally well, but in others it was a bit underwhelming. The rapid file transfer ended up being surprisingly helpful, and in my tests with the 128GB version DJI’s claim of up to 600 MB/s transfer speed over USB 3.1 holds up, and I found it a huge time-saver compared to sending lots of files wirelessly.

The camera’s battery life is a limitation, though, particularly when shooting at higher resolutions like 4K/60fps. I got closer to 60 minutes of continuous recording here – rather than the 90 minutes that DJI claims at 1080p/24fps – which isn’t bad for its size, but lags behind the multi-hour endurance of larger cameras like the Osmo Action 5 Pro. The dock can top up the battery on the go, and I was also impressed by its ability to charge to 80% in just 20 minutes, especially if you’re as bad as I am at remembering to charge your gear before a shoot.

You then get up to 200 minutes of 1080p/24fps video from the dock, but in reality, I found this closer to two hours once the screen and Wi-Fi are on and you’ve powered the camera up and down a few times.

If you tend to record short clips throughout a longer day, it’s nothing to worry about. If you’re the type of shooter to record continuously, you may lament the fact that there aren’t replaceable batteries to swap out when you run out of juice. I left the camera running for my battery tests during a particularly warm day, and although it felt hot to the touch during, it never overheated to the point of turning off.

(Image credit: Lauren Scott)

The Osmo Nano is equipped with DJI’s RockSteady 3.0 stabilization and HorizonBalancing. It handles a fair amount of shake, but it’s not on the same level as a dedicated gimbal like the Osmo Pocket series. In footage of fast-paced, high-impact activities like running on trails you’ll still see some micro-jitters, but for walking shots it’s pretty impressive.

Using different mounts will dictate how stable your results are. Using the pendant seemed to cause me more wobbles than handholding the camera, for example, but the head mount gave me super-smooth footage when running. It’s worth noting that there are different levels of stabilization, with daily, sport, or anti-motion blur options. You can also turn off image stabilization to save battery, or if you’re using a secondary DJI product to keep things stable.

The DJI Osmo Nano performs really well in remote shooting scenarios without a phone. The voice commands, like ‘start recording’, work almost instantaneously in a quiet environment, but require you to shout when it’s loud (not a great look in a city center). I found that gestures worked well too, and I liked being able to pat the camera when it was powered off to start recording, or nod my head when it was mounted on my head. Much more subtle.

(Image credit: Lauren Scott)

The Osmo Nano has two built-in microphones for stereo sound, and I found the audio straight out of the camera surprisingly immersive. It picks up sound from a variety of directions when you’re shooting in a public place, but still hones in on your voice when you’re speaking to the camera clearly.

Like all action cameras, the audio quality sounds muffled underwater, but the clarity returns more quickly than others I’ve tested when you pull the camera back out into fresh air. There are lower and stronger wind reduction modes, and both did a decent job of reducing disturbance when I captured some clips on a blustery countryside walk, without removing the noise entirely (see the clips below). My voice was clear and free from distortion, but it’s not the perfect solution for clean audio; for that, you’ll need a separate mic.

A major draw is the ability to connect the Osmo Nano directly to DJI’s wireless microphones without needing a separate receiver. I haven’t been able to try this yet, but I can see it being convenient for creators who want to capture high-quality audio, especially those already with DJI mics.

DJI Osmo Nano: Image quality

  • 1/1.3-inch sensor
  • Video up to 4K/120fps and 35MP photos
  • 10-bit D-Log M and HLG color profile options

The Osmo Nano has a 1/1.3-inch sensor, the same size as you’ll find in the Osmo Action 5 Pro and just a fraction smaller than the one in the Insta360 Go Ultra. Video headlines include 4K at 60fps in 16:9 format, and 4K 120fps slow-mo footage, which expands to 1080p 240fps.

The specs are one thing, but the proof is in the pudding; or in this case, in the videos and shots you get from the camera. Overall, I think the image quality is good for an action camera of this size. As ever, it won’t completely replace a full-sized or full-frame camera, but that’s not the expectation here. The fixed 143-degree ultra-wide field of view is perfect for first-person POV shots, and I could fit a whole wedding group in the frame (I don’t have permission to include the sample shot in the review, sadly), but it’s not easy to zoom in on the scene should you want to get closer in.

I tested the Osmo Nano in all weather and lighting scenarios. DJI touts the wide dynamic range of the Osmo Nano, but in direct sunshine I noticed some banding where the highlights had been clipped. You can see this in the video above, which was a test of the one-tap editing feature in the DJI Mimo app.

4K resolution is sharp and punchy, and even in 8-bit color mode the camera seems to capture vibrant blue skies and leafy greens, and handles quick changes in light (coming out of a dark tunnel, from indoors to outdoors) well; however, while I like a bit of lens flare, this is one area that could be handled better. It tended to keep my face exposed when I was talking to the camera, but this wasn’t set up anywhere in the camera. If I were to generalize, I’d say footage comes out darker than Insta360’s Go Ultra, possibly for greater leeway when editing, where the Insta option is designed for near-automatic use.

DJI’s SuperNight mode does a decent job of reducing noise in low light, but it only works at up to 30fps and with 8-bit color, which might limit its utility for serious cinematographers. It’s the best night image quality in a wearable camera I’ve seen, but it’s still bound by the laws of physics – a smaller lens and sensor will always have certain limitations compared to a larger, more dedicated camera. There’s some AI-smoothing being applied to reduce noise in low-light footage, but this is less obvious to the untrained eye, and less muddy than some night modes I’ve seen on earlier action cameras.

DJI’s automatic horizon leveling (which can be calibrated) is pretty flawless, and the RockSteady image stabilization is most impressive in sports mode. To really test it out, I wore the camera on DJI’s headband mount and recorded the first five minutes of a high-intensity workout. Throughout a gruelling round of burpies, star jumps and squats, the footage was stable and smooth (almost unnaturally so). Trail runs, dog walks, and cycle clips were all just as usable, but the handheld results are slightly more jittery than using a dedicated mount.

Photos from the camera have a medium-range megapixel count (the maximum resolution is 35MP and you can shoot in a 16:9 or 4:3 ratio), and as to their quality, I said the same thing about Insta360 Go Ultra’s photo results: they’re good enough to insert into videos, but I probably wouldn’t use them for standalone social posts or prints as a creator. Consider them as an additive rather than a standalone feature, and you won’t be disappointed.

Image 1 of 4

(Image credit: Lauren Scott)(Image credit: Lauren Scott)(Image credit: Lauren Scott)(Image credit: Lauren Scott)

Impressively, the Osmo Nano gives you the option of recording footage with a flat color profile (DJI’s D-Log M setting), designed to preserve the maximum color and brightness info in the video file, especially in lights and darks.

While the footage out of the camera is desaturated in this mode, I found you had far more wiggle room to adjust the colors, contrast, and saturation to achieve a specific, cinematic look without losing any of the detail captured in the original scene. This is also going to benefit creators shooting a project with the Osmo Nano alongside other cameras who want their edited work to look consistent.

DJI Osmo Nano: testing scorecard

Swipe to scroll horizontallyDJI Osmo Nano

Attributes

Notes

Rating

Price

Much cheaper than the Insta360 Go Ultra, and that includes helpful built-in storage.

5/5

Design

Unexciting but functional, and it’s a shame the dock is only splash-proof. The lens replacement adds ruggedness.

4/5

Performance & features

Fewer filters and modes than the Insta360 Go Ultra, but you get the option of manual controls. The DJI Osmo app makes quick, clever edits.

4/5

Image quality

In daylight, colors are vivid and dynamic range is good. Stabilization is excellent, and low light footage is fine. Slow-mo could be crisper.

4/5

Should I buy the DJI Osmo Nano?

Buy it if…

You want a camera that ‘disappears’
The Osmo Nano is small enough to be worn on a pendant, hat, or headband, thanks to its small size and weight. The magnetic mount allows for quirky mounting solutions like lamp posts, cars, and even washing machines.

You already own DJI products
To boost the sound quality, you can connect the Nano directly to two DJI microphone transmitters without needing a receiver. If you’ve already got a DJI mic, gimbal or camera, sticking with the brand also means greater familiarity with the app.

Don’t buy it if…

You like a roomy LCD screen
At less than two inches, I found the Osmo Nano’s LCD touchscreen a little small for composing shots and reviewing footage. You can use your phone for a larger live view, but this isn’t always convenient.

You want a fully waterproof solution
The Nano’s Vision Dock is only splashproof, and this made me uncomfortable while shooting in the rain or near water. If you’re a real action lover, I’d recommend a camera with a more rugged build.

Also consider

The Insta360 Go Ultra has a similar form factor, with a separate camera and action pod. The flip-up screen is more vlog-friendly and bigger at 2.5 inches, while the camera weighs the same as the Osmo Nano but is more square and shallow (which I found easier to mount). Pricing and image quality are similar, but it’s a slightly more fun action camera that’s great for the whole family.

Read my full Insta360 Go Ultra review

The GoPro Hero 13 Black is still the flagship of action cams and one I’d recommend for serious filmmakers. It’s chunkier than the Osmo, but it also has magnetic mounting. GoPro also has the widest range of mount accessories to open up creative shooting opportunities, and it’s possible to squeeze 1.5 hours of 5.3K video from the battery, for recording with fewer interruptions.

Read our full GoPro Hero 13 Black review

(Image credit: Lauren Scott)

How I tested the DJI Osmo Nano

  • I tested the camera for two weeks pre-embargo
  • I wore it on walks and runs, and mounted it for drives
  • I recorded videos at all settings and in all modes

DJI sent me a full-production Osmo Nano for review around two weeks before its release date, and I used it at least once a day – often much more – during this period. I always like a camera to become a natural part of my workflow, rather than carrying out one intense period of testing, so that I uncover the nuances for a more informed and helpful review.

I tried all the camera’s modes, used it with and without the dock, and mounted it on the magnetic pendant and headband. I mainly used the DJI Mimo app to edit footage right from my iPhone 15 Pro.

  • First reviewed September 2025

DJI Osmo Nano: Price Comparison



Source link

0 comments
0 FacebookTwitterPinterestEmail
Decrypt logo
GameFi Guides

Nano Banana Saves Google: Gemini Dethrones ChatGPT as GOOG Hits $3 Trillion

by admin



In brief

  • Google’s Gemini to #1 in app downloads this month and Search interests this week.
  • This is the first time Gemini app dethrones ChatGPT.
  • This also helped boost Google’s valuation to beat $3 trillion, just behind Nvidia, Apple and Microsoft.

Google’s Gemini app hit the top of the Apple App Store on September 15, dethroning ChatGPT for the first time since OpenAI’s chatbot launched nearly three years ago. The catalyst wasn’t a breakthrough in artificial general intelligence or some new reasoning mode—after all, Gemini 2.5 was released in March—it seems to be the public’s thirst for making memes and editing images.

“Image editing is one of the most popular use cases for Nano Banana,” the company tweeted last week. While Google didn’t provide any specific reasons for its come-from-behind surge in popularity, given the timing, it’s safe to assume that Nano Banana gave the company a huge bump.

One specific prompt for Google’s new image editing model let users transform photos into 3D collectible-style portraits complete with plastic packaging and display bases. That was enough to make the Gemini have its “wen moon” moment.

Within two weeks of going viral in early September, Gemini hit #1 on both the Apple App Store and Google Play Store globally. The app added 23 million first-time users and users generated over half a billion images in days, according to Google’s VP Josh Woodward.

Update: In the last 4 days, @GeminiApp has added:
+ 13M more first-time users (23M+ total now)
+ 300M more images (500M+ total now)

🍌 @NanoBanana is unreal

— Josh Woodward (@joshwoodward) September 8, 2025

Google Trends data shows global searches for Gemini overtook ChatGPT on September 12—the first time that’s happened since ChatGPT’s November 2022 debut.

Image: Google Trends

Before Nano Banana, Gemini pulled in about 13 million monthly downloads compared to ChatGPT’s 64 million, according to AppMagic. ChatGPT commanded 60% of AI-related web traffic with nearly 6 billion monthly visits, almost 10 times Gemini’s numbers despite being integrated into Android devices and Google services used by 2 billion people.

The surge helped push Alphabet’s market cap past $3 trillion, with shares climbing 4% to around $252. That puts Google’s parent company in rarefied air alongside Nvidia ($4.3 trillion), Microsoft ($3.8 trillion), and Apple ($3.5 trillion).

Image: companiesmarketcap.com

Alphabet’s stock has climbed nearly 30% year-to-date, outpacing the Nasdaq’s 15% gain. The September milestone came after a favorable antitrust ruling that avoided forcing Google to divest Chrome or Android. But the Nano Banana phenomenon contributed directly to investor enthusiasm. Analysts project the feature could help Google increase its revenue through new Gemini subscriptions.

“If Gemini can remain at the top of the App Store charts, we believe more investors will start to view Gemini as a strong core offering with incremental use cases that complement (as opposed to cannibalize) the core search experience,” Keybanc Capital analyst Justin Patterson wrote in a report.

OpenAI learned this lesson months ago. Its “Ghiblify” feature—which transformed photos into Studio Ghibli-style animations—drove more than 1 million people to sign up for ChatGPT in one hour. The feature went so viral that OpenAI had to implement rate limits after users generated millions of whimsical portraits, even recreating controversial moments like the 9/11 terrorist attacks in the Ghibli style.

xAI discovered the same dynamic with Grok, though Elon Musk’s company took a different approach. When Grok users found they could generate anime-style “waifus” without the content restrictions other AIs imposed, downloads spiked 300% in Asian markets. Musk himself posted several generated images on X, alongside a “spicy mode” that let users generate NSFW videos using Grok’s AI

Vibes have shifted fully.
Gemini has overtaken ChatGPT on the AppStore rankings and now worldwide in Search Interest as well.

It’s a no-brainer that image editing is the sole reason for this. Nano banana has rescued Google in the AI race!

🤏🍌
🤏🍌
🤏🍌 https://t.co/cHEhKyalzz pic.twitter.com/YD2eusnthW

— Taufiq (@taufiqintech) September 15, 2025

ChatGPT still dominates on raw metrics—700 million weekly active users and over 1 billion daily queries in the last quarter, but Gemini’s sudden rise shows how quickly the landscape can shift when an AI feature catches fire on social media.

Google DeepMind CEO Demis Hassabis tweeted: “Congrats to the @GeminiApp team… this is just the start.”

Let’s hope there are more memes to come.

Generally Intelligent Newsletter

A weekly AI journey narrated by Gen, a generative AI model.





Source link

0 comments
0 FacebookTwitterPinterestEmail
Decrypt logo
GameFi Guides

How to Use Google’s Nano Banana AI to Transform Your Selfies Into Digital Figurines

by admin



In brief

  • The free Gemini 2.5 Flash Image tool turns selfies into hyperrealistic 1/7-scale figurines, sparking explosive demand.
  • Users simply upload a full-body photo, paste a detailed prompt, and receive toy-store-ready results in seconds.
  • 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.

Update: In the last 4 days, @GeminiApp has added:
+ 13M more first-time users (23M+ total now)
+ 300M more images (500M+ total now)

🍌 @NanoBanana is unreal

— Josh Woodward (@joshwoodward) September 8, 2025

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.

How to turn yourself into a figurine, for free

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.

Generally Intelligent Newsletter

A weekly AI journey narrated by Gen, a generative AI model.





Source link

0 comments
0 FacebookTwitterPinterestEmail
Google AI Figurines
Gaming Gear

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

by admin



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.

Toying with AI

Figurine me (Image credit: Google)

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.

Puppy pose

“Firecracker Fido”. (Image credit: Google)

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.

You might also like



Source link

0 comments
0 FacebookTwitterPinterestEmail
Close