Latest news with #KatelynChedraoui
CNET
4 days ago
- CNET
Adobe Wants You to Use AI to Stop Poorly Photoshopping Images
At its very core, Photoshop is a compositing program -- able to combine multiple images into one project. So it's not totally surprising, in this era of generative AI, to see that this core photo editing activity has gotten an AI-powered boost. Harmonize is the newest Photoshop beta feature. Named after the photo harmonization process, the tool helps seamlessly match an image to a project by naturally blending objects into the background. It uses AI to create a new lighting environment, including adjustments to coloring and shadows. With one click of the Harmonize button, Photoshop will create a kind of invisible layer and apply it over the image, making it blend nearly perfectly with the rest of the project without destroying either image. The before-and-after shots are dramatic, and it aims to cut down what can be a grueling, detail-oriented editing process to mere minutes. An example of what the harmonize tool can do. The original headshot (left) is illuminated to create a completely relit shot (right). Adobe/Screenshots by Katelyn Chedraoui Photoshop users got a peek at this tool when it was just a research concept at last fall's Adobe Max creator conference. At the time, I spoke with Adobe Applied research scientist Mengwei Ren, one of the lead engineers on the project, about what potential this tool had for Photoshop users. I followed up this month now that the feature made its official beta debut. Old editing problems, new AI tricks After a "very shocking" positive reaction from the Max live audience, in Ren's words, she and the Photoshop team worked to refine the tool. The beta tool, out now, was spurred on by Max and is the culmination of years of machine learning and imagery work. "We've tried to solve it in different ways," Ren said. "We started with just trying to do relighting on faces, then we also tried a separate model for adding shadows only. At some point, because the gen AI technology is really evolving, and then we started to think wild, like, 'OK, can we really bring this into one unified model?'" Which is part of what powers the Harmonize tool now. In the months since Max, the team has enhanced the tool's resolution to get higher-quality outputs, created more precise controls to give users pixel-level alignment and expanded its training dataset to help the tool create accurate lighting conditions for any image. (Adobe's AI user guidelines and terms say it doesn't train on customer content and its models are trained on licensed content, including Adobe Stock and public domain content.) Faster, smoother compositing is something the Adobe team has been working on for nearly a decade, Stephen Nielsen, senior director of product management for Photoshop, told CNET. Pre-AI era work to improve selection and background removal tools set the foundation for Harmonize. Generative AI technology helped pull all the different pieces of the puzzle together and make it quick for people to use. "Often people talk about something being poorly Photoshopped, and a lot of it has to do with how well you match the lighting, the color tone and the shadows. This makes it so much faster, efficient and easier to achieve a really good composite," Nielsen said. Like any beta tool, especially with AI involved, Harmonize isn't perfect. Future work will focus on maintaining a higher level of quality when being used on more intricate objects, like human faces. Preserving the identity of faces is "the trickiest thing to solve," Nielsen said, and will be an area of continued research. "The expectation, especially from pro users, is pro commercial results. In many cases, you can get that, depending on the assets that you're combining with Harmonize. In some cases, more work needs to be done to refine the output," Joel Baer, director of product management for Photoshop, told CNET. "We know there are some [use cases] we need to continue to optimize for and continue improving." As of now, you'll need to use the beta desktop app or web app to use any of these new AI tools. The Harmonize feature is additionally available through the Photoshop iPhone mobile app. Adobe subscription plans that include Photoshop start at $20 per month. Read More: I Took Photoshop's Generative AI for a Spin. These Are the Tools That Stuck Out An example shown during Adobe Max 2024. Neither person in this image was originally here. Using the harmonize tool, the lighting is adjusted for seamless visual consistency. Adobe/Screenshot by Katelyn Chedraoui Photoshop AI in 2025 Harmonize is the latest step on Photoshop's longer AI journey. Two other gen AI changes coming for Photoshop users are a new generative upscaling tool and upgrades to its generative remove feature. Upscaling is a common generative AI process that improves an existing image, like by clarifying and adding finer details. In this case, the Photoshop tool promises to boost image resolution up to 8 megapixels. More pixels means your imagery should be sharper and clearer. The newly updated remove tool should be more precise when selecting objects to erase, and the affected area should blend more seamlessly for a cleaner final edit. The goal for adding AI in Photoshop is to enhance the work of, not replace, human editors, Nielsen said. But many creators are worried about the development and deployment of generative AI, from the alleged copyright infringement taking place during model training to the AI slop filling online spaces and job security worries. For more, check out the first AI feature in Premiere Pro and Adobe's new Indigo camera app.
CNET
23-07-2025
- CNET
Here's How to Hide AI-Generated Images in Search Results in DuckDuckGo
With a new tool built into DuckDuckGo's privacy-focused search engine, you can hide AI-generated images from your search results, which could help ensure you see fewer misleading or fake photos. The filter isn't on by default, though, so you have to enable it. Here's how. 1. Go to 2. Search for an image, something like "baby peacock." 3. Go to the Images tab. 4. Click AI Images: show to open a dropdown menu. 5. Click Hide. DuckDuckGo DuckDuckGo said in an email to CNET that the image filter relies on open-source blocklists from uBlockOrigin and uBlacklist Huge AI Blocklist. CNET's Katelyn Chedraoui covers AI, like chatbots and image generators, and she thinks tools like this are a great way to give people more control over their search experiences. However, she said these tools aren't perfect. "AI images are impossible to escape online," Chedraoui said. "There's no silver bullet for weeding out AI." DuckDuckGo conceded in its email to CNET that this filter won't stop every AI-generated image result. But the company said that the filter "will greatly reduce the number of AI-generated images you see." The company said it plans on adding more filters in the future. For more on DuckDuckGo, here's what to know about the privacy-focused search engine, five reasons why you should use it and what to know about its VPN service.
CNET
18-07-2025
- CNET
This Search Engine Lets You Hide AI-Generated Images in Search Results
DuckDuckGo, the company behind the privacy-focused search engine, now has a new tool built into its search engine that lets you filter out AI-generated images from your search results. That way, you may see fewer misleading or fake photos when looking for images. However, the filter is not on by default, so you have to enable it. Here's how to use the AI-generated image filter in DuckDuckGo. 1. Go to 2. Search for an image, something like "baby peacock." 3. Go to the Images tab. 4. Click AI Images: show to open a dropdown menu. 5. Click Hide. DuckDuckGo DuckDuckGo said in an email to CNET that the image filter relies on open-source blocklists from uBlockOrigin and uBlacklist Huge AI Blocklist. CNET's Katelyn Chedraoui covers AI, like chatbots and image generators, and she thinks tools like this are a great way of giving people more control over their search experiences. However, she said these tools aren't perfect. "AI images are impossible to escape online," Chedraoui said. "There's no silver bullet for weeding out AI." DuckDuckGo conceded in its email to CNET that this filter won't stop every AI-generated image result. But the company said that the filter "will greatly reduce the number of AI-generated images you see." The company said it plans on adding more filters in the future. For more on DuckDuckGo, here's what to know about the privacy-focused search engine, five reasons why you should use it and what to know about its VPN service.
CNET
18-06-2025
- Entertainment
- CNET
How To Fix the Most Common AI Image Errors and Hallucinations
One of the best parts of my job is laughing at the truly terrible, deeply flawed, occasionally frightening AI images that pop out while I review different AI image generators. I spend a lot of time playing around with AI in ChatGPT, Midjourney and Adobe, and I've learned that no AI generator is perfect. But there are some common patterns, things that many AIs struggle with. Every image generator is unique, but I've spent enough time with them to recognize some patterns. There are certain things AIs are prone to mess up -- fingers on hands, overlapping elements, extremely fine details, etcetera. Some AI image programs give you tools to edit these mistakes, which is great. But when you can't, these are my tried-and-true tips for tweaking your prompts and settings to fix your images. These are the biggest problems I found and how to fix them. For more, check out the best AI image generators and our guide to effective AI image prompt writing. Human faces and expressions Katelyn Chedraoui via Canva Magic Media AI/CNET Accurate facial expressions continually challenge AI generators. Quirky eyes, teeth and eyebrows are some of the strongest indicators that an image is AI-generated. In this case, the result was extremely funny to me, if also completely unusable. The girls are sporting some Halloween-like vampire teeth, and the dude in the back is having more than a bad hair day. Stephen Shankland via Dall-E 3/CNET Even with cartoon or non-realistic characters, generators struggle to moderate emotion and expressions. This image -- created by our best pick, Dall-E 3 -- over-amplified the prompt, and the end result was too dramatic. I'm a self-identified neat freak, but I can't imagine anyone getting this upset over what looks like hundreds of dollars of cleaning supplies. Even the best programs can fail and produce wonky results. How to fix it: I recommend asking the service to cut down on the number of people it's trying to render -- cut down on the number of chances for error -- and using post-generation editing tools to select specific parts of the image that need regenerated or fixed. Picking a more mild adjective ("angry" rather than "enraged") might help guide the service down the right path. Iconic characters, trademarks and recognizable logos Katelyn Chedraoui via Canva Magic Media AI/CNET For many reasons, AI image generators can rarely produce accurate logos, known trademarks or otherwise recognizable characters. This is usually because there are significant legal concerns about a company allowing its brand materials or intellectual property to be used for AI services. It also could be because the logo or brand you want to include isn't in the generator's training data, so the generator won't understand your request. Two recent exceptions to this are new image generation features on the Google Pixel 9 and Pixel 9 XL, thanks to Gemini AI, which our mobile experts used to create images featuring accurate-looking Mickey Mouse and Pikachu renditions. The other exception is some paying X (formerly Twitter) users reporting that they can use the social media site's Grok chatbot to make realistic-looking Mickeys and human political figures. These images still aren't perfect renderings, but they're pretty close. How to fix it: You can't, but on the plus side, you're a lot more likely to avoid lawsuits for copyright infringement. If you run into this issue, I recommend rethinking your design concept to see if you can get the same point across without using a specific company name or logo. Do you really need the TikTok logo, or do you just need a phone with a vertical video playing, for example. Overlapping, complex elements Katelyn Chedraoui via Leonardo AI/CNET Occasionally, you'll stump a generator if you have too many overlapping or complex elements within an image. The best AI image programs aren't going to run into this issue very often, but even the best programs fail at some point. With this Leonardo image, the library of my dreams is ruined by the rolling ladder that disappears halfway up. Katelyn Chedraoui via Canva Magic Media AI/CNET Similarly, this photorealistic image of a kitchen looks alright from a cursory look, but a second glance or quick zoom-in shows nonsensical characters printed on the cookbook, and the book itself seems to have two spines and three sections. Images like this show how frustrating it can be to create AI images -- even when you think you've got a winner, small flaws make them unusable. How to fix it: Try simplifying your prompt or using post-generation editing tools to single out the problem and fix it. Sometimes changing the aesthetic can help as well; these issues usually pop up when you're trying to make photorealistic or stock images. If your service offers a specific area editing tool, try using that to select the questionable area and ask the generator to remove what's in it. Over-editing and hallucinations Katelyn Chedraoui via Midjourney AI/CNET The sign of a great AI image generator is its ability to produce an image with few errors or hallucinations while giving you the right tools to fix those issues when they inevitably pop up, but not every service does. In this example from Midjourney, I went through several rounds of edits on this image of a soccer team celebrating a victory, and I have no idea what happened to get to this final result -- or any clue what's going on with the blob that's presumably a player in the right-hand side of the picture. Frankly, I don't think Midjourney knew either. How to fix it: With editing AI images, sometimes less is more. Don't be afraid to scrap your current batch of images and start over. You can often preemptively fix big issues by refining your prompt so you only have to worry about fixing minor issues later. AI generators still need human work Katelyn Chedraoui via Leonardo AI/CNET I have no doubt that the companies behind these AI generators are working to eliminate these issues and level up their models. For now, imperfect images show us once again that while this tech is improving, it's not flawless. My hope is that because so many of these services face similar challenges, they will all be chasing solutions for these issues. As a final note, I'll remind you that it's a best practice to credit or acknowledge that an image is AI-generated when you share it. As AI images get better and more realistic-looking, it's more important than ever to distinguish AI-generated art from other kinds of media. For more, check out our advice for writing the best AI image prompt and our best picks for AI image generators.
CNET
15-05-2025
- Business
- CNET
Meta Reportedly Delays 'Behemoth' AI Model: What This Could Mean for Its AI Tools
Meta has reportedly pushed back the release of its Behemoth large language model for its artificial intelligence tools, delaying it until the fall. Behemoth was originally planned to release in April to coincide with Meta's first AI conference, LlamaCon, but was delayed until June before being delayed again now, according to a report by The Wall Street Journal on Thursday. Meta released Llama 4 in April. Llama -- Large Language Model Meta AI -- is Meta's family of LLMs. But Meta AI engineers are concerned the capabilities in the Behemoth LLM aren't a significant enough improvement over what's already available via Llama 4 to warrant a release next month, according to WSJ citing unnamed sources within Meta. A large language model is what sits behind the chatbot interface you interact with when you ask AI tools like ChatGPT, Gemini and Meta AI a question. LLMs understand and generate human-like text. Behemoth is "one of the smartest LLMs in the world and our most powerful yet to serve as a teacher for our new models," Meta said in April. The tech giant aims to become one of the biggest AI providers, and has already woven AI into how you interact on many of its apps across Facebook, Instagram, WhatsApp and Messenger, including helping with writing posts and captions, and editing your images. Meta also released a standalone app for Meta AI at the end of April, which includes a hub for its Ray-Ban smart glasses. CNET social media and AI reporter Katelyn Chedraoui, who reported on LlamaCon in April, said this fresh delay adds to concerns that Meta is already behind the curve on what its AI tools are capable of. "Meta's reported decision to delay the release of its new Llama models means the company could fall even further behind other big companies like OpenAI and Google," Chedraoui said. "The race to build advanced and affordable AI is extremely competitive. The concern for Meta is how far ahead competitors will advance while it's still working on refining the models it has already announced." Meta didn't immediately respond to a request for comment.
