Observe ZDNET: Add us as a most popular supply on Google.
ZDNET’s key takeaways
- Photos 2.0 delivers correct textual content and usable graphics.
- It might match model types, together with ZDNET visuals.
- Errors nonetheless slip in, requiring human overview.
Earlier this week, OpenAI unveiled ChatGPT Photos 2.0, its new picture technology engine. Key to this launch is a bounce in performance from creating “decorations” (OpenAI’s time period) to full-page graphics, together with detailed textual content.
I had early entry to a pre-release model. It labored fairly properly, however saved messing up on the ZDNET emblem. Now that the product has been formally launched, I am giving it an in-depth check throughout a variety of challenges.
Photos 2.0 is out there to all ChatGPT tiers, however the extra succesful language options are solely out there to paying tiers that may use the Considering mannequin. I am working all these assessments utilizing a ChatGPT Plus account with Considering turned on.
Additionally: I put GPT-5.5 by way of a 10-round check: It scored 93/100, shedding factors just for exuberance
Let’s get began with the ZDNET branding workout routines. Relatively than simply importing ZDNET pages and having it discover the brand on the web page, I created a standalone picture of the ZDNET emblem and uploaded that with every immediate. That appeared to assist tremendously.
[One quick note: ZDNET doesn’t permit OpenAI to scrape its pages. Ziff Davis, ZDNET’s parent company, filed an April 2025 lawsuit against OpenAI, alleging it infringed Ziff Davis copyrights in training and operating its AI systems. So I used a Chrome extension to capture full-screen screenshots of the articles I wanted to test with Images 2.0. That’s how ChatGPT was able to read them.]
Can Photos 2.0 protect the ZDNET emblem?
My start line was the article I beforehand wrote about Photos 2.0. I fed ChatGPT this immediate: “Create a detailed and vivid infographic of this article using the ZDNET brand style and the attached ZDNET logo.”
Not solely is the brand appropriate, however the coloring is ideal for ZDNET. However the place the picture actually shines is its use of textual content. All of the textual content is appropriate, even the tiny textual content on an angle within the picture.
Can it produce styled sketchnotes?
Subsequent, I made a decision to revisit the sketchnotes problem I gave to Google’s Nano Banana just a few months in the past. The project at the moment was to create a sketchnotes model of the US Invoice of Rights. Nano Banana did an incredible job with the pictures, however I needed to attempt again and again (and over) to persuade it to get the wording proper. Learn the article to see the hoops I needed to bounce by way of.
Additionally: I used Nano Banana 2 to make excellent sketchnotes: 5 classes realized
For ChatGPT Photos 2.0, I upped the stakes barely. I needed sketchnotes, however I needed them in ZDNET’s branding fashion. I am taking part in up the branding fashion all through this text as a result of that is a method ChatGPT Photos 2.0 might present actual worth to customers.
This is the primary immediate: “Make me a sketchnote of the US Bill of Rights. Use the ZDNET logo style and make the sketchnotes in the ZDNET style.” That is the picture on the left. This is the second immediate: “Include the ZDNET logo and add more neon-style colors, perhaps on a black background.” That is the picture on the proper.
First, discover that the textual content is appropriate. There aren’t any duplicates. Nothing is lacking. Already, that is head and shoulders above Nano Banana’s efficiency. Each variations match with ZDNET’s fashion. The one factor I am not thrilled with is that the ZDNET emblem appears to be like jammed in on the second picture. Even so, the brand is appropriate, and I might most likely do just a few extra immediate passes to get it positioned higher.
Wacky enjoyable with an infographic
However now we come to the unforced error my testing set revealed. I requested Photos 2.0 to transform my AI web site builder shootout article to an infographic. It produced a reasonably usable, if considerably busy, infographic. It even went to the web and added data I did not have within the article, like base pricing.
However there are 4 clear errors:
- The header highlights “here are 9 of the best AI website builders.” It even makes the “9” stand out. Besides that solely 5 web site builders had been reviewed. Decrease within the infographic, it exhibits the 5 I do overview. Oops.
- The providers I reviewed had been Hostinger, GoDaddy, Wix, 10Web, and Squarespace. ChatGPT determined, for some purpose, to interchange 10Web with Sturdy (a competitor to 10Web). I did not overview Sturdy. I did not even point out Sturdy. Wacky.
- The AI produced a abstract desk for the providers, itemizing star scores for ease of use, design flexibility, and AI options. However I did not present star scores for these classes. The AI was overly beneficiant towards some distributors, in a manner that was instantly opposite to the overview textual content itself. Odd.
- Lastly, and this can be a nit, however nonetheless. Means down on the backside, the place the AI appropriately reproduced the ZDNET emblem, there is a drooping line simply above it. Why?
Additionally: The perfect AI picture turbines: There’s just one clear winner now
To be honest, these are all errors an in-house human graphic designer may produce in a primary draft. In my years as a founder and a product supervisor, I’ve actually seen extra egregious graphics errors come again from my designers on their first drafts.
Once I re-prompted Photos 2.0 with corrections (aside from the star scores, which I did not appropriate within the second picture), it did appropriately modify the infographic with extra applicable data.
ChatGPT Photos has come a good distance
This Photos 2.0 launch is a big enchancment over earlier variations. The ChatGPT Photos model I checked out final 12 months was spectacular, particularly for recontextualizing photographs.
Additionally: I obtained an early take a look at ChatGPT Photos 2.0, and it is spectacular – with one exception
This new model, which might interpret precise content material after which create photographs, is a big leap over earlier builds. Extra to the purpose, it will probably ship very tangible enterprise worth, which makes it value quite a bit not just for enjoyable photos however for actual work.
Keep tuned, as a result of I will be how this construct compares with Google Gemini’s Nano Banana. I will be pushing it even additional to see what different work-related duties it will probably assist with, notably relating to consumer interface design.
How comfy are you counting on AI-generated visuals, figuring out that the mannequin can introduce delicate factual errors? Tell us within the feedback under.
You may observe my day-to-day venture updates on social media. Remember to subscribe to my weekly replace publication, and observe me on Twitter/X at @DavidGewirtz, on Fb at Fb.com/DavidGewirtz, on Instagram at Instagram.com/DavidGewirtz, on Bluesky at @DavidGewirtz.com, and on YouTube at YouTube.com/DavidGewirtzTV.
