In its announcement, OpenAI pitched the new ChatGPT Images as a serious creative tool, with professional-level results. With all the caveats about the limits of AI image generators, it is a bit like a slightly flawed but high-powered visual production studio with someone running it who understands regular language, so you don’t have to mess with sliders and layers.<\/p>\n
<\/p>\n The new model comes with some changes to ChatGPT, too. There\u2019s now a dedicated “Images” tab inside ChatGPT that serves as a hub for making images, with pre-built filters and curated options based on current trends. There are also templates that let you generate or edit images without even typing a prompt. You can click \u201cretro magazine layout\u201d or \u201cfuturistic food styling\u201d and see how it looks without having to work out the best phrasing for a prompt, part of OpenAI’s efforts to make the tool as accessible as possible.<\/p>\n You may like<\/p>\n There are a lot of other subtle improvements to the new model as well. It can produce denser text without devolving into nonsense, show a crowd of small faces without producing too many oddballs, and it can keep track of elements across multiple edits, so you can change one aspect of an image without the AI deciding to mess with other bits. Past models were easily confused by chain edits or overlapping instructions.<\/p>\n The upgrade also makes for better combining and transforming of images. You can ask it to blend styles, move an aspect of one image to another, or remove everything except a single component and move it into a new setting. You also don’t have to worry so much about the space between people or objects getting confused.<\/p>\n AI image enhancement<\/p>\n Still, it\u2019s not perfect. Some outputs miss the mark. Occasionally, the model will misinterpret a phrase or render something too literally. But the difference now is that those moments feel like exceptions rather than the norm. Or at least that’s what OpenAI claims.<\/p>\n There’s more to it than just what you can do with OpenAI’s model. Adobe<\/a> recently revealed that it is embedding Photoshop<\/a> and Acrobat into ChatGPT. That means we\u2019re approaching a future where multiple editing platforms live side by side. You might prompt ChatGPT to design a poster, then click over to Photoshop to refine it, without ever leaving the same window.<\/p>\n ChatGPT doesn’t lack for AI image competition from the likes of Google<\/a> Gemini and Midjourney, but the casual access to ChatGPT Images means you might turn to it for producing things like an improved LinkedIn headshot before you specifically open Midjourney.<\/p>\n The most positive interpretation of the upgraded ChatGPT Images is that another level of high-quality visual creativity is no longer gated by technical skill or expensive software. But that comes with all of the caveats and uncertainties about how much of what ChatGPT produces is simply remixed content scraped without consent from human artists, not to mention how much its use takes away opportunities for professionals in the field. As much fun and as impressive as the results can be, it still means that users have to decide what exactly it means to \u201cmake\u201d something in the first place.<\/p>\n Follow TechRadar on Google News<\/a> and add us as a preferred source<\/a> to get our expert news, reviews, and opinion in your feeds. Make sure to click the Follow button!<\/p>\n And of course you can also follow TechRadar on TikTok<\/a> for news, reviews, unboxings in video form, and get regular updates from us on WhatsApp<\/a> too.<\/p>\n The best business laptops for all budgets<\/p>\n Our top picks, based on real-world testing and comparisons![\"Purple](\"https:\/\/www.newsbeep.com\/uk\/wp-content\/uploads\/2025\/11\/1763875814_869_hhZUEBD3xpcxphhUVzPa5G.png\")
<\/p>\n
\n