ChatGPT Images 2 made me a perfect magazine — then I realized I couldn’t do anything with it

ChatGPT Images 2 made me a perfect magazine — then I realized I couldn’t do anything with it

AI-generated image of three magazines on a table
(Image credit: OpenAI)

The new ChatGPT Images 2 are now available on all different ChatGPT subscriptions, including Free. This is a much improved version of the original ChatGPT Images that features more accurate image generation, especially small text, more aspect ratios for images, and paid users now benefit from reflection-enabled workflows, allowing them to reason through an image generation task and even search the web where they need to find more basic information.

One of the things ChatGPT can now do, and which really caught my attention when Sam Altman demonstrated the feature in his introductory video, was create what look like real magazines from text and photo prompts. ChatGPT can create magazine covers, as well as entire pages from within, such as content pages and editorials.

Article continues below

How to create a magazine in ChatGPT

To create a magazine cover, simply give ChatGPT a photo and ask it to turn it into a magazine cover using a prompt like:

(Image credit: OpenAI / Apple)

The prompt is: “I want to make this a magazine cover featuring these two men. One is Tom.[sic] Cook (right) and John Ternus are on the left. Tetanus[sic] succeeds Cook as Apple CEO. So let’s see a dynamic business magazine cover.

In response, ChatGPT is creating something that resembles a well-designed magazine – at least on the surface.

(Image credit: OpenAI / Apple)

Text generation used to be the real Achilles heel of AI image generation, so this is really impressive. The text in AI images regularly degenerated into gibberish symbols, but is now clear and relevant. But then you start to notice the little things…

For example, there are periods at the end of sentences, which you sometimes see on magazine covers, but this is not the usual style of magazines. And the cover lines are repetitive, which isn’t surprising given that there isn’t much information on ChatGPT. If you were to actually use this image for a professional project, you’ll have to start making changes, and that’s where things fall apart.

Sign up to receive the latest news, reviews, opinions, best tech deals and more.

The big problem is that it’s a graphic, so I can’t just load it into InDesign and edit the text like I normally would with a magazine cover I was working on. And that got me thinking: what’s the point then?

I quite often have the same reaction to all the impressive things that AI can do, especially around images: what’s the point? Who is it for? Why would you want to do that?

Recently, Google announced that Gemini can now access your Google Photos, so it can reproduce images of you in familiar situations similar to those in your photos, but in a cartoon style or with plasticine characters. I mean, it’s very impressive, but why?

I suppose you could share the images with your family members, but that will get very tiring, very quickly. You can imagine the teenagers’ eye rolls: “Uh oh, here comes Dad with the AI ​​slop again…”

I have similar thoughts about this magazine cover. Maybe it’s useful as a proof of concept if you’re considering creating a magazine… but how many people using ChatGPT are seriously considering creating a print magazine? And if they were, they would create something in appropriate software, like Adobe InDesign, where you can edit the text and move the headings.

Can ChatGPT replace designers?

I wouldn’t be surprised if, after the ChatGPT Images 2 product announcement, people said that ChatGPT can now create magazines, or posted the cover images they created and said things like “Goodbye art directors.” But we’re just not there yet.

Producing an image is a long way from creating something that could fit into a real magazine production workflow. It’s only when you dig deeper that things start to break down, which is true for much of AI-produced content.

I don’t expect ChatGPT to do anything that a proper desktop publishing program like Adobe InDesign could do, but I’m also tired of all the “now AI can do that!” headlines. » features that turn out to be more about impressing shareholders than providing anything practical and useful. And that looks like a model that’s starting to define a lot of AI announcements right now.

Maybe I should be grateful that AI can’t replace me yet, even though it’s very good at generating things that look like it could.


Follow TechRadar on Google News And add us as your favorite source to get our news, reviews and expert opinions in your feeds.


Replace this – registration here for a relevant ecoms block to include. If there isn’t one, include a Hawk widget instead

Graham is AI Editor at TechRadar. With more than 25 years of experience in online and print journalism, Graham has worked for a variety of market-leading technology brands, including Computeractive, PC Pro, iMore, MacFormat, Mac|Life, Maximum PC, and many more. He specializes in reporting on all things AI and has appeared on BBC TV shows like BBC One Breakfast and on Radio 4 to comment on the latest technology trends. Graham has an honors degree in computer science and spends his free time creating podcasts and blogging.