Observe ZDNET: Add us as a most well-liked supply on Google.
ZDNET’s key takeaways
- OpenAI reframes photos as a visible language.
- Pondering mode builds context-aware infographics.
- Model constancy remains to be inconsistent in early testing.
Right this moment, OpenAI introduced ChatGPT Pictures 2.0, its next-generation picture mannequin, which the corporate says is targeted on precision, usability, and complicated visible duties.
Essentially the most notable new functionality is the flexibility to mix textual content and pictures to construct complicated, lovely pages. OpenAI is reframing the entire concept of picture technology from a course of that creates decorations (their phrase) to a language (additionally their time period).
Additionally: One of the best AI picture mills of 2026: There’s just one clear winner now
OpenAI describes it as, “An excellent picture does what a superb sentence does — it selects, arranges, and divulges. It may well clarify a mechanism, stage a temper, take a look at an concept, or make an argument.”
Pondering capabilities allow complicated workflows
Along with its vastly improved means to combine textual content and graphics, the brand new mannequin makes use of enhanced considering capabilities. It may well generate a number of photos per immediate with continuity throughout outputs. This method is feasible as a result of the mannequin really integrates reasoning into the picture output.
This shift is huge. As an alternative of simply producing a picture that just about matches the immediate particulars, Pictures 2.0 can take a a lot vaguer immediate, like “Generate an infographic about actions I ought to do with tomorrow’s climate in San Francisco in thoughts.”
Additionally: The best way to change from ChatGPT to Gemini
From this immediate, the AI will collect climate and exercise knowledge about San Francisco, decide actions applicable to the climate, after which construct a picture or set of photos that match the outcomes.
In accordance with OpenAI, “On this mannequin, Pictures 2.0 acts extra like a visible thought associate, serving to carry a venture from tough idea to completed asset with considerably much less work in your half.”
Precision and design management enhance usability
Many people have lengthy struggled to persuade ChatGPT to generate photos in a particular desired facet ratio. Usually, the AI stubbornly produces what it desires. However now, with Pictures 2.0, the mannequin has assist for “facet ratios as huge as 3:1 and as tall as 1:3.”
The mannequin additionally helps higher-fidelity outputs that (largely) produce correct object placement, detailed textual content rendering, and complicated compositions. We’ll see if we will take away the phrase “largely” from that sentence after the product is formally launched.
Additionally: I attempted Private Intelligence, and it was correct (however unsettling)
The AI additionally helps small textual content, UI parts, and stylistic constraints at as much as 2K decision. Cool.
Testing the preview
I used to be given entry to a day-before-release preview, and the mannequin is spectacular, largely. I fed it a screenshot of the ZDNET dwelling web page and a draft of the Pictures 2.0 press launch.
Then I instructed, “Based mostly on the contents of the press launch, generate a 16:9 infographic concerning the new picture replace and generate it utilizing the ZDNET model fashion as proven within the ZDNET dwelling web page doc.”
Additionally: I attempted Google Photographs’ new AI Improve device: The way it crops, relights, and fixes your pictures – typically
The mannequin did an excellent job on the infographic, however attempt as it’d, it couldn’t reproduce the ZDNET brand. On its first attempt, it rendered the Z in ZDNET with a slight droop.
I attempted a wide range of requests on the order of, “Repair the ZDNET Emblem. The Z droops in your model however shouldn’t be droopy within the precise brand.” However Pictures 2.0 by no means managed to repair it.
So I began a brand new session. This time, I included the instruction, “Use particular care to breed the ZDNET brand precisely.”
Additionally: I examined ChatGPT Plus vs. Gemini Professional to see which is best – and if it is value switching
This is the place issues obtained very odd. For its first run, the mannequin by some means dug up a duplicate of ZDNET’s brand from earlier than our 2022 redesign. This brand is nowhere to be discovered on our present dwelling web page. Weirdly, it rendered that previous brand utilizing the present shade scheme. The mannequin then pushed the brand and the infographic data off the left fringe of the picture. It additionally selected a lightweight blue for “Pictures 2.0” that is not a ZDNET model shade.
I attempted mightily to persuade it to make use of the present brand. I managed to get it to push the picture to the correct, so nothing was minimize off. However including the immediate, “Use the ZDNET brand that’s on the offered web page. Don’t seek for another brand,” did nothing to repair the issue.
I took yet another shot on the problem earlier than deciding to return to ending up this text. As soon as once more, I began a brand new session so the AI did not have muscle reminiscence from its earlier miscalculations.
Additionally: This highly effective Gemini setting made my AI outcomes far more private and correct
The mannequin tousled the brand once more. This time, the AI determined so as to add a rudder form to the stem of the stretched-out capital D.
To be truthful, I am utilizing a pre-release model of Pictures 2.0. I will be again with a way more complete take a look at run of the mannequin after the official product launch.
I additionally tried an identical take a look at utilizing a unique doc with Google’s Nano Banana Professional, however as a result of it did not deal with the synthesis the way in which that this new model of OpenAI’s product does, it wasn’t actually capable of repeat the outcomes I obtained right here. We’ll know extra as we do extra superior assessments
Pricing and availability
The brand new mannequin is obtainable right this moment to all ChatGPT and Codex customers. Superior outputs and the considering functionality can be found to ChatGPT Plus, Professional, Enterprise, and Enterprise customers. You should definitely choose “Pondering” from the ChatGPT dropdown bar on the high of the display.
On the time of writing, earlier than launch, the brand new Pictures 2.0 mannequin is simply out there on the desktop. However OpenAI guarantees that these capabilities might be within the cell model as properly, together with the flexibility to finger-select photos utilizing your cell touchscreen.
The photographs are additionally out there through API utilizing the gpt-image-2 mannequin. API pricing varies relying on the standard, thinkiness (my phrase), and desired picture decision.
If an AI can deal with structure and content material together, will that change the way you method design initiatives? Tell us within the feedback beneath.
You’ll be able to comply with my day-to-day venture updates on social media. You should definitely subscribe to my weekly replace e-newsletter, and comply with 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.