The ability of AI services to generate images is well recognized and one of the most common uses of services like ChatGPT. It is also an area that has been surrounded by controversy – photographers, artists and filmmakers are upset that Open AI and other companies have “trained” their AI models on their copyrighted works. In this guide, I gather tips on what you can do and how to get better results. Create images from text The most obvious thing you can use ChatGPT to do with images is to generate something completely new. Just give prompts like “create a picture of two rabbits playing in a meadow” or “make a photorealistic picture of a woman sitting in front of a computer drinking coffee out of a cup that says PC for Everyone” and an image will pop up that you can download and use. In many cases the images ChatGPT generates are really good, or at least good enough to use, but sometimes they don’t match what you asked for, or have obvious errors. Today, errors like too many fingers or an extra hand in a group photo are not as common, but errors that cannot be ignored are still common. When this happens, you can either try to continue in the same chat and try to get ChatGPT to tweak the image until the result is better, or try again with a new or modified prompt. Which works best will vary and you will simply have to try it out. ChatGPT first generated the image on the left. When I asked it to change it so that she is holding the cup in her left hand, I got the image on the right – note that the gaze has been wrong.Bilder genererade av Chat GPT In my experience, the results of small adjustments rarely improve enough to be worth the effort and so-called prompt engineering, where you try out different formulations, is far from an exact science. Even an adjustment that is logically very small, like adding “one of the rabbits has a pink collar” or “she’s holding the cup in her left hand” to the examples above, can lead to totally different results – or be exactly as you hope. 5 tips for better photos with ChatGPT Skärmdump Describe what you are looking forHave a picture in your head of what you want? Describe it as if you were telling someone who can’t see what you see. “A girl with brown hair and pale skin sitting at a piano in an old house with old-fashioned furnishings” is better than “a girl sitting and playing the piano” if that’s exactly how you want the image. If you don’t have a clear picture yourself, ChatGPT has nothing to go on. Sure, it can produce interesting results from time to time to see what happens when the AI is given a freer rein, but if you’re after something in particular, you need to actually say what it is. Avoid overly detailed descriptionsA detailed description is important, but it can also be too much. If you write a whole A4 page with an extremely detailed description, there is a high probability that ChatGPT will lose the thread and produce something unusable. Include the essentials but let the AI fill in the rest. InPixell_Studio “Metadata”Do you want a wide image or a square one? Should it look like a photo or a painting? Should the colors be saturated or faded? How much of the image should the main subject take up? Should the light be warm or cold, sharp or soft? Tell ChatGPT how the picture should be made, not just what it should contain. Try it againDidn’t get it quite right? Ask ChatGPT to try again, or ask it to create some different suggestions. Change the prompt and see if it gives better results. Try a more detailed description – or vice versa, a simpler one, if your original prompt was already very detailed. Start from a sketchIf you can draw a simple sketch that shows the basic composition and content of the image you’re after, you can ask ChatGPT to turn it into a finished image in any style. How well this works varies widely. Common problems include illogical composition, facial expressions that don’t match the sketch, and most of all, people looking in the wrong direction. Editing and improving your own images In addition to generating brand new images, you can use ChatGPT to edit existing images. It’s important to note that this isn’t really editing in the usual sense of the word. Every time you ask it to make a change, it generates the whole image again, it’s just that the algorithm works in such a way that most of the new image will be identical to the original. Skärmdump Once ChatGPT has created an image, you can click on it to open the chatbot’s editing interface. There’s really only one tool here, plus buttons for undo and redo. Click on the edit tool and your mouse pointer will turn into a big circle when you hover it over the image. Click and drag to paint an area that marks the part of the image where you want ChatGPT to make the changes you then ask for. This could be things like removing a distracting object, changing the details of something (like changing the print on a jumper visible in the image) or adding something new. If you want to make more general changes, you can do so directly in the prompt without selecting anything. “Remove background” often works well in its simplicity, but other changes may need a bit more detailed descriptions. Anders Lundberg Sometimes ChatGPT gets itself to make more changes than requested. Then you can try to specifically tell it not to change anything else. For example: “Change the color of the umbrella to red. Do not make any other adjustments or changes to the image.” “Zoom, enhance” A very common trope in films is that a detail is needed from a blurry photo or still from a surveillance film, and all a “computer person” needs to do is zoom in on the image and click an Enhance button. Sometimes a high-resolution version showing the necessary details pops up instantly, but sometimes the story requires it to take time, and then the computer can keep thinking for a long time. Often part of the image is shown at a time and the tension is unbearable as pixel after pixel appears on the screen. This is science fiction, of course. Information that doesn’t exist can’t be ‘recreated’ no matter how advanced an algorithm or how powerful a computer. But with AI, it can be faked. Any feature that removes distracting objects or people and fills in the background uses machine learning of some kind, whether it’s called AI or not. Older techniques like Photoshop’s content-aware fill use simpler algorithms while some newer ones use the same algorithms that AI chatbots do when generating new images. I asked ChatGPT to enlarge and fill in the missing details in this photo.Anders Lundberg The result ChatGPT spat out – not too bad.Genererad av Chat GPT Enlarging an image works in a similar way, but instead of guessing what fits to fill in a larger gap, the algorithm guesses how many small gaps to fill in so that the image is sharper (shows more detail). Since some of the information is already there, the risk of the AI coming up with something completely wrong is much lower. If you can already see what a sign says in a low-resolution image and the AI just makes the text clearer, it hasn’t lied, although it can’t be said to have recreated lost information. The result will never be identical to what it would have been if the image had simply been taken at higher resolution or better sharpness, but in most cases that difference is an academic question – what matters is whether you can use the image at the size you want without it looking blurry. ChatGPT is particularly good at making people sharp.Anders Lundberg Another thing you can try is to ask ChatGPT to sharpen a blurred image, for example a photo where the camera focused wrong. This can work really well if the image is only slightly blurry, but if it’s very blurry it guesses wildly and then the person in the photo can look like someone else entirely. Apply a certain style to images ChatGPT has become known for being good at a particular kind of editing – turning a photo or other image into a picture with a particular style. You’ve probably seen examples of the trend to ask ChatGPT to make images in Studio Ghibli style, that is, with a cartoon style similar to films directed by Hayao Miyazaki. It’s very good at it, but be aware that the creators you make it mimic have in most cases been sharply critical of the move. Some have sued Open AI for copyright infringement. Less controversial is asking ChatGPT to change the image to a style that is not that of any individual artist, for example “turn this photo into a watercolour painting”, or asking for a style that belongs to a long-dead artist like Rembrandt. Foto: Anders Lundberg, målning genererad av Chat GPT You can also upload an existing image to have as a reference and ask ChatGPT to remake other uploaded images to match the style of that image. A trick you can try if this does not give satisfactory results is to upload the example in a new chat instead and ask ChatGPT to “generate a description of the image that could be used to ask ChatGPT to apply the same style to another image”. Paste the results into the chat where you have uploaded the image(s) you want to change the style of. Skärmdump Gallery In the top left column of ChatGPT, under New Chat and Search Chats, you will find the Gallery feature. It’s a repository for all the images you’ve generated with ChatGPT (technically only with the GPT-4o model, not images generated with the older Dall-e model). It makes it easier to find specific images you have generated, so that you can, for example, continue working or look up how you wrote the prompt at the time. Click on an image and then on Open in chat in the top right corner to go to the thread where the image was generated. Skärmdump Generate video with Sora In addition to image generation, Open AI has developed algorithms that can generate video, and is offered as a separate service called Sora, with its own website and app. Sora is not embedded in ChatGPT mainly because the service requires a more advanced user interface, and Open AI wants to keep ChatGPT’s simple interface. Sora is exciting and can create scarily realistic videos. Going through everything you might find useful about video generation would take up more space than I have in this guide. But you can start from the same basic tips as for image generation. My second tip is to try and play around with the service. But keep in mind that you can create a maximum of 15 10-second clips a day unless you have an expensive Pro subscription. Skärmdump Projects and GPTs Just like with text, you can use projects to keep all of your chats organised and add files and instructions to accompany any new chats in that project. This is ideal if, for example, you’re using ChatGPT to create image resources for a website or anything else where you want to stick to a consistent style. If you pay for a Plus subscription, you can also use the GPT feature to create customised versions of the chatbot, not to mention accessing GPTs created by other users, like the upscaling GPT I mentioned above. Read more about the benefits of projects and GPTs here. AI-generated images and copyright If you let ChatGPT or another AI service generate images for you, you have no copyright on them. It doesn’t matter how detailed your description was or how much you fiddled with the prompt. This means that others can copy ‘your’ images and use them, without asking you and without you being able to do anything about it. It is also illegal to claim that you own the copyright to an AI-generated image. However, if you take an AI-generated image and make major changes to it using a program such as Photoshop, it can become a “work of authorship”, which gives you the copyright to it. The same applies if you paint an image that the AI has generated – then it is your painting that you have the copyright to, not the generated original. The US Library of Congress has a good guide to AI and copyright, which also warns of the risk of an AI infringing someone else’s copyright. If you’re just using the images for personal use, there’s a low risk of you being sued, for example by Studio Ghibli if you’ve made a portrait of yourself “Ghibli-style”, but for those running a business, it’s more important to be careful. Read...

The executive has admitted receiving commercial sexual services from an underage girl in September. Read...

In 2026, ANZ businesses that master agile AI, sovereign data, subscription models and energy efficiency will set the pace for growth. Read...

Physical security is evolving into a strategic business function, with AI, unified platforms and hybrid cloud reshaping priorities to 2026. Read...

Egmont Honey is finding global success with its brand of manuka honey despite being late to the expanding market. Read...

The Labour Party leader says the summer break can be good for business as everyone is on holiday all at once. Read...

At a glanceExpert`s Rating Pros Strong AMD CPU performance Lots of RAM and a big SSD Generous port selection Good speakers Cons Display is on the dim side Grainy webcam Battery life is behind the most efficient ultraportables Our Verdict The Asus ExpertBook P3 is a work-focused laptop that shines in its price range. AMD’s hardware once again delivers Microsoft’s modern “AI PC” experience without the compromises Intel and Qualcomm make. Price When Reviewed This value will show the geolocated pricing text for product undefined Best Pricing Today Best Prices Today: Asus ExpertBook P3 Retailer Price $1,229.99 View Deal Price comparison from over 24,000 stores worldwide Product Price Price comparison from Backmarket Best Prices Today: Check today’s prices The 14-inch Asus ExpertBook P3 is a work-focused Copilot+ PC that delivers a surprisingly nice body — all-metal build quality, a snappy keyboard, and unusually good speakers — with AMD internals that deliver serious performance. For many workers, the serious multithreaded CPU performance here will be more important than a laptop that could theoretically last 24 hours away from a power outlet. Asus delivered an excellent package here, and I’m a fan… mostly. I wasn’t particularly impressed by the display on my review model, and the webcam is a weak point. But the overall package is superior to the average business laptop and far superior to the average Copilot+ PC when it comes to CPU performance. Asus ExpertBook P3: Specs The Asus ExpertBook PM3406CKA is a business laptop with an AMD Ryzen AI processor. Our review model came with an AMD Ryzen AI 7 350 processor, Radeon 860M graphics, 32GB of DDR5 RAM, and a 1TB solid-state drive. Asus listed it at a price of $1,479 on its website, but it was on sale for less, $1,229 on Amazon at the time the review was being completed. While AMD’s Ryzen AI hardware can’t quite deliver the battery life you’ll find on Qualcomm Snapdragon X or Intel Lunar Lake hardware, it does deliver an incredible combination of traditional x86 hardware (unlike Qualcomm Snapdragon X), strong multithreaded CPU performance (unlike Intel Lunar Lake), and a Copilot+ PC-ready NPU (unlike Intel’s other hardware). Battery life is still solid. It’s just not the 20+ hour runtimes I’ve seen on Intel Lunar Lake and Qualcomm Snapdragon X Elite and Snapdragon X Plus hardware. At the time of the review, Asus was selling models of this machine with an AMD Ryzen AI 5 330 CPU and AMD Radeon 820M graphics starting at $949. Model: Asus ExpertBook PM3406CKA CPU: AMD Ryzen AI 7 350 Memory: 32GB DDR5 RAM (5600 MT/s) Graphics/GPU: AMD Radeon 860M NPU: AMD NPU (up to 50 TOPS) Display: 14-inch 1920×1200 IPS display with up to 60Hz refresh rate Storage: 1 TB PCIe Gen4 SSD Webcam: 1080p camera Connectivity: 2x USB Type-C (USB 3.2 Gen2), 2x USB Type-A (USB 3.2 Gen1), 1x HDMI 2.1, 1x combo audio jack, 1x RJ-45 Gigabit Ethernet, 1x Kensington Nano lock slot Networking: Wi-Fi 7, Bluetooth 5.4, Gigabit Ethernet Biometrics: Fingerprint sensor and IR camera for Windows Hello Battery capacity: 70 Watt-hours Dimensions: 12.31 x 8.94 x 0.71 inches Weight: 3.6 pounds MSRP: $1,479 as tested This is a robust laptop that can deliver impressive performance with reasonable battery life and at a fair price. Asus ExpertBook P3: Design and build quality Foundry / Chris Hoffman The Asus ExpertBook P3 has an all-metal chassis. Asus calls it a “robust aluminum build” and says it meets US MIL-STD 810H testing standards for performing in difficult conditions. While my review workflow doesn’t include dropping laptops or subjecting them to sandstorms, this machine did feel incredibly robust. Design-wise, you’re getting a silver chassis with a black keyboard and a black bezel around the display. The beveled edges at the edge of the laptop’s keyboard tray are shinier. It looks and feels like a very rugged, very professional business laptop. This 14-inch all-metal build and 3.6-pound chassis feels well-designed. Even the hinge feels carefully designed: Unlike many laptops, I can open the laptop’s display with just a single hand. The hinge keeps the display nicely in place, and I don’t have to use two hands to open the machine. Asus ExpertBook P3: Keyboard and trackpad Foundry / Chris Hoffman The Asus ExpertBook P3 has a chiclet keyboard with a 1.5mm key travel depth. It feels snappy and responsive, and it was a pleasure to type on. The white backlight makes it readable in low-light conditions. The large trackpad also feels excellent. The click-down action has a particularly nice tactile feel — it quickly springs back after you click it down. The surface was smooth and responsive. I prefer haptic trackpads, but this is quite a nice mechanical trackpad. Asus ExpertBook P3: Display and speakers Foundry / Chris Hoffman The Asus ExpertBook P3 has a 14-inch IPS display with a 1920×1200 resolution and a 60Hz refresh rate.  That’s a reasonable resolution, but the refresh rate is just average. The big problem is the brightness. With just 300 nits of maximum brightness, there’s no way around it: This isn’t a particularly impressive display. That’s common for work-focused PCs, which tend to go for displays that deliver longer battery life and prioritize other specs over a visual “wow” factor. This display does have a nice anti-glare coating, which makes it more readable in challenging lighting conditions. For people using this PC on the go, the display will probably be the biggest drawback: More brightness would be a real upgrade. This laptop’s speakers sound unusually good for a business machine in this price range. There’s more bass than I would expect, they get plenty loud, and the high notes can get bright and crisp in songs like Steely Dan’s Aja, an audiophile standard benchmark. Asus ExpertBook P3: Webcam, microphone, biometrics The Asus ExpertBook P3 has a 1080p webcam, and it wasn’t particularly impressive. The image quality seems grainy and washed out. On a snowy day in New England, the daylight wasn’t enough to provide a crisp picture, and neither was my office’s overhead lighting. The webcam is the one component here that feels like it doesn’t quite match the quality of the rest of this machine. This machine does have a physical webcam shutter switch, which is always nice to see. This laptop’s built-in microphone setup sounds surprisingly good, too. The audio quality of my voice was deeper and richer than it normally is on the average laptop I review. I’d be happy using this to speak in online meetings, although I wish the webcam delivered a better image quality. The ExpertBook has an IR camera for Windows Hello facial recognition sign-ins, as well as a fingerprint reader built into the power button at the top-right corner of the keyboard. You can use whichever biometric method you like. Asus ExpertBook P3: Connectivity Foundry / Chris Hoffman The Asus ExpertBook P3 packs an excellent selection of ports. On the left, you’ll find two USB Type-C ports, a USB Type-A port, an HDMI 2.1 port, and a combo audio jack. On the right, this machine has a second USB Type-A port, an RJ-45 Ethernet jack, and a Kensington Nano lock slot. That’s an excellent selection of ports, including Ethernet, but be aware there’s no SD card reader here. Also, this machine charges via USB Type-C, so you’ll always be plugging the charging cable into the left. I wish there was a USB Type-C port on each side of the machine, though. The USB Type-C ports are USB 3.2 Gen2, so there’s no Thunderbolt or USB4 here. The Asus ExpertBook P3 supports Wi-Fi 7 and Bluetooth 5.4, so you have the latest bleeding-edge wireless hardware. Combined with Gigabit Ethernet, this machine is ready for all sorts of network setups on the go. Asus ExpertBook P3: Performance The Asus ExpertBook P3 performed well in day-to-day productivity tasks — web browsers, office suites, communication tools, and the type of Windows desktop apps most workers would be running on laptops like this one. We ran the Asus ExpertBook P3 through our standard benchmarks to see how it performs. Foundry / Chris Hoffman First, we run PCMark 10 to get an idea of overall system performance. With a PCMark 10 score of 7,636, the Asus ExpertBook P3 exceeded the performance you’d get from Intel Lunar Lake-powered Copilot+ PCs. Foundry / Chris Hoffman Next, we run Cinebench R20. This is a heavily multithreaded benchmark that focuses on overall CPU performance. It’s a quick benchmark, so cooling under extended workloads isn’t a factor. But, since it’s heavily multithreaded, CPUs with more cores have a huge advantage. With a multithreaded Cinebench R20 score of 6,213, the Asus ExpertBook P3 and its eight cores with 16 threads exceeded Intel’s eight-core Lunar Lake hardware, which is focused on efficiency and not multithreaded CPU performance. Foundry / Chris Hoffman We also run an encode with Handbrake. This is another heavily multithreaded benchmark, but it runs over an extended period. This demands the laptop’s cooling kick in, and many laptops will throttle and slow down under load. The Asus ExpertBook P3 completed the encode process in an average of 974 seconds, or just over 16 minutes. That’s an excellent score, especially for a Copilot+ PC laptop. Foundry / Chris Hoffman Next, we run a graphical benchmark. This isn’t a gaming laptop, but it’s still good to check how the GPU performs. We run 3Dmark Time Spy, a graphical benchmark that focuses on GPU performance. With a 3DMark Time Spy score of 3,037, the AMD Radeon 860M graphics here just aren’t as powerful as what Intel offers in Lunar Lake systems. However, they’re nowhere near the bottom-of-the-barrel older “Intel Graphics” GPUs that many lower-end laptops are currently shipping with. Overall, performance was excellent for a machine like this one. If you prioritize graphics performance, however, you’ll want a machine with a different GPU (likely a discrete GPU). Asus ExpertBook P3: Battery life The Asus ExpertBook P3 has a 70 Watt-hour battery. Combined with AMD Ryzen AI 7 350 hardware, I’d expect to see decent battery life for a laptop, but not maximum ultraportable battery life. And that’s exactly what the benchmarks showed. Foundry / Chris Hoffman To benchmark the battery life, we play a 4K copy of Tears of Steel on repeat on Windows 11 with airplane mode enabled until the laptop suspends itself. We set the screen to 250 nits of brightness for our battery benchmarks, which meant we had to crank this laptop’s display brightness up. This is a best-case scenario for any laptop since local video playback is so efficient, and real battery life in day-to-day use is always going to be less than this. The Asus ExpertBook P3 lasted an average of 768 minutes, which is 12.8 hours. Depending on your workload and your screen brightness, you may be able to get a full workday of battery life out of it, but just barely. The battery life is okay, but battery life is a trade-off you make when you choose AMD Ryzen AI hardware. They offer decent power efficiency, but you get more performance than you do with Intel Lunar Lake and Qualcomm Snapdragon X hardware, and you pay for it with higher power consumption. Asus ExpertBook P3: Conclusion The Asus ExpertBook P3 is a great laptop combining an all-metal build quality and “AI PC” hardware that delivers a combination of solid CPU performance and an NPU that can drive Microsoft’s Copilot+ PC features. On top of that, the price — $1,200 to $1,400 or so, depending on the sale pricing — is an excellent value for a machine that comes with 32GB of RAM and a 1TB solid-state drive. The main downside here is the display: Many people will want something brighter and perhaps higher-resolution. The other downside here is battery life: Chips from Intel and Qualcomm will deliver much longer battery life at the cost of top-end CPU performance, and that will be a better fit for workers with light workflows. But this is a robust laptop that can deliver impressive performance with reasonable battery life and at a fair price. It’s a great laptop. Read...

Businesses that treat AI as a shiny toy, not a planned tool, risk waste, security gaps and stagnation as competitors move ahead. Read...

How an unusual business selling adult toys has found opportunity on the main street of Eketahuna. Read...

We honour the best in news, sport, business and entertainment. Read...