Quite a bit has modified within the AI business within the 4 months since OpenAI launched ChatGPT Pictures 1.5. We have seen a heated race to construct agentic instruments, an unprecedented cope with the Pentagon and never-ending AI slop.
Now, OpenAI is again within the generative media recreation. The corporate introduced on Tuesday that it is releasing ChatGPT Pictures 2, its next-generation picture mannequin.
ChatGPT Pictures 2 is supposed to create text-heavy designs, like on this matcha commercial and pretend journal cowl.
It could appear unusual that OpenAI is releasing a brand new picture mannequin only a month after saying the shuttering of its once-viral Sora AI video app with the intention to give attention to constructing enterprise-ready “core merchandise.” But it surely’s clear from how the brand new mannequin was constructed that OpenAI is not backtracking on that objective.
ChatGPT Pictures 2 is designed to supply text-heavy photographs, together with infographics, scientific posters, research guides and advertising supplies. The times of bizarre Sora movies and Studio Ghibli-inspired memes are over.
Now, the corporate is constructing AI that may do what it calls “economically worthwhile inventive duties.”
“The aperture and use circumstances for visible intelligence simply increase so broadly, and we imagine that that is so important to ChatGPT’s imaginative and prescient for growing your personal private assistant, as a result of your inventive assistant is a large a part of who you might be as a person,” Adele Li, product lead for ChatGPT Pictures, advised reporters in a press briefing.
(Disclosure: Ziff Davis, CNET’s mum or dad firm, in April 2025 filed a lawsuit in opposition to OpenAI, alleging it infringed Ziff Davis copyrights in coaching and working its AI techniques.)
In these examples, you may see how a lot better ChatGPT Pictures 2 is at rendering legible textual content.
OpenAI has been chasing the dream of a brilliant app, a one-stop store for all issues AI, constructed out of its Codex platform. ChatGPT Pictures 2 is bringing the inventive piece of that puzzle.
The brand new mannequin naturally improves typography, iconography and composition to supply extra skilled AI photographs. It could possibly generate textual content in a number of languages. AI picture fashions have notoriously struggled with creating legible, factually right textual content. ChatGPT Pictures 2 is OpenAI’s greatest mannequin for that but. Google beforehand improved its textual content rendering with Nano Banana Professional, however even that “better of the perfect” mannequin struggled with accuracy.
ChatGPT Pictures 2 is rolling out to all customers now. Your era restrict relies on your plan: The extra you pay, the extra AI photographs you may generate.
Builders utilizing the mannequin within the API can create photographs in 2K and 4K decision, although these greater resolutions are nonetheless in beta and could also be wonky. Paying customers can even create photographs utilizing considering and reasoning fashions, which assist them search the net for info, compile it right into a readable design and double-check their work.
“Picture mannequin” does not appear to be fairly the correct time period for ChatGPT Pictures 2, although it’s technically right. ChatGPT does not seize the fantastical surrealism of AI imagery like Midjourney, nor supply wherever close to the modifying instruments of Adobe Firefly.
But it surely’s catering to a gaggle of customers in the course of the spectrum of Midjourney’s creative fanatics and Adobe’s skilled creators: those that have to create engaging content material.
Like Anthropic’s newly launched Claude Design, OpenAI’s ChatGPT Pictures 2 is aimed toward working professionals. Lecturers can use it to create research guides and illustrated lesson plans. Advertising and marketing managers can create social media posts and visible belongings.
You may create as much as eight photographs from a single immediate, like a three-page report, that keep visible consistency throughout all of them.
You may make longer studies with ChatGPT Pictures 2, all matching pages.
That is the second half the AI-generated key lime pie recipe. Discover the visible consistency.
One draw back is that if you wish to tweak an AI picture, you will nonetheless have to regenerate it. With extra text-heavy designs, that is extra more likely to be vital, so you will run by means of your credit faster. OpenAI mentioned it is centered on sustaining its iterative, prompt-based modifying movement to maintain it straightforward to make use of.
OpenAI’s security procedures have not considerably modified since its final picture mannequin. It nonetheless contains metadata by means of the C2PA customary, so AI photographs’ origins may be recognized. Abusive and unlawful imagery continues to be prohibited in OpenAI’s insurance policies, an essential guardrail for AI firms to successfully implement, given current examples of AI-generated deepfakes and nonconsensual intimate imagery.