Observe ZDNET: Add us as a most popular supply on Google.
ZDNET’s key takeaways
- OpenAI reframes photographs as a visible language.
- Considering mode builds context-aware infographics.
- Model constancy remains to be inconsistent in early testing.
As we speak, OpenAI introduced ChatGPT Pictures 2.0, its next-generation picture mannequin, which the corporate says is concentrated on precision, usability, and sophisticated visible duties.
Probably the most notable new functionality is the flexibility to mix textual content and pictures to construct advanced, lovely pages. OpenAI is reframing the entire concept of picture era from a course of that creates decorations (their phrase) to a language (additionally their time period).
Additionally: The perfect AI picture mills of 2026: There’s just one clear winner now
OpenAI describes it as, ” picture does what a great sentence does — it selects, arranges, and divulges. It could possibly clarify a mechanism, stage a temper, take a look at an concept, or make an argument.”
Considering capabilities allow advanced workflows
Along with its vastly improved potential to combine textual content and graphics, the brand new mannequin makes use of enhanced pondering capabilities. It could possibly generate a number of photographs 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 large. 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: swap from ChatGPT to Gemini
From this immediate, the AI will collect climate and exercise information about San Francisco, decide actions applicable to the climate, after which construct a picture or set of photographs that match the outcomes.
In line with OpenAI, “On this mannequin, Pictures 2.0 acts extra like a visible thought accomplice, 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 photographs in a particular desired side ratio. Typically, the AI stubbornly produces what it desires. However now, with Pictures 2.0, the mannequin has help for “side ratios as extensive 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 sophisticated 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 residence web page and a draft of the Pictures 2.0 press launch.
Then I instructed, “Primarily based on the contents of the press launch, generate a 16:9 infographic concerning the new picture replace and generate it utilizing the ZDNET model type as proven within the ZDNET residence web page doc.”
Additionally: I attempted Google Images’ new AI Improve instrument: The way it crops, relights, and fixes your photographs – generally
The mannequin did a terrific 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 quite a lot of requests on the order of, “Repair the ZDNET Brand. The Z droops in your model however will not 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 price switching
Here is the place issues obtained very odd. For its first run, the mannequin one way or the other dug up a duplicate of ZDNET’s brand from earlier than our 2022 redesign. This brand is nowhere to be discovered on our present residence web page. Weirdly, it rendered that previous brand utilizing the present colour 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 colour.
I attempted mightily to persuade it to make use of the present brand. I managed to get it to push the picture to the suitable, 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 one more 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 the same take a look at utilizing a special 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 in a position to repeat the outcomes I obtained right here. We’ll know extra as we do extra superior checks
Pricing and availability
The brand new mannequin is offered at present to all ChatGPT and Codex customers. Superior outputs and the pondering functionality can be found to ChatGPT Plus, Professional, Enterprise, and Enterprise customers. Remember to choose “Considering” from the ChatGPT dropdown bar on the high of the display screen.
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 will probably be within the cellular model as effectively, together with the flexibility to finger-select photographs utilizing your cellular touchscreen.
The pictures 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 tasks? Tell us within the feedback under.
You’ll be able to comply with my day-to-day venture updates on social media. Remember to subscribe to my weekly replace publication, 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.
