【????? ????? ??????】OpenAI's ChatGPT and Sora get native image generation

OpenAI has native image generation in ChatGPT and ????? ????? ??????Sora.

In a livestream led by CEO Sam Altman as well as members of OpenAI team, the company demoed new capabilities in image generation that's driven by the GPT-4o model.

SEE ALSO: A new AI test is outwitting OpenAI, Google models, among others

Previously, image generation relied on OpenAI's DALL-E text-to-image model. Now, GPT-4o handles the image generation, meaning it has the world knowledge and contextual understanding to generate images more seamlessly and conversationally. The model's responses will understand contextual prompts without specific reference to an image, can follow prompts for reiterating on a generated image, and OpenAI says it's way better at rendering text.

---

You May Also Like

---

---

Text rendering looks to be way better. Credit: OpenAI

With image generation in ChatGPT, OpenAI's goal is to make it more useful rather than just a novelty. That means it can generate diagrams, infographics, logos, social media posts, and other graphics. In Sora, there's now a new section for generating images (in addition to videos) much like the Midjourney interface.

Mashable Light Speed Want more out-of-this world tech, space and science stories? Sign up for Mashable's weekly Light Speed newsletter. By clicking Sign Me Up, you confirm you are 16+ and agree to our Terms of Use and Privacy Policy. Thanks for signing up!

In the livestream, Altman said that the model leans into "creative freedom," saying "what we'd like is for the model to not be offensive if you don't want it to be, but if you want it to be within reason, really let people create what they want."

Altman seemingly tried to clarify this in an X post, saying, "what we'd like to aim for is that the tool doesn't create offensive stuff unless you want it to, in which case within reason it does. As we talk about in our model spec, we think putting this intellectual freedom and control in the hands of users is the right thing to do, but we will observe how it goes and listen to society."

This Tweet is currently unavailable. It might be loading or has been removed.

In case that didn't totally make sense to you either, OpenAI's stance on blocking images that violate its content policy "such as child sexual abuse materials and sexual deepfakes," remains the same.

According to the accompanying blog post, all images have C2PA metadata, which provides invisible watermarks detailing an image's provenance.

Native image generation for ChatGPT is available today for ChatGPT Plus, Pro, Team, and Free users within the chat experience, with access rolling out to Enterprise and Edu users soon.

• relaxation
• recreation
• knowledge
• explore
• fashion
• synthesize
• hotspot
• focus

• ‘Mazinger Z: Infinity’ to Be Screened
• All the iOS 18.5 features I recommend trying after updating
• D6 Pro Plus massage gun deal: $60 off at Amazon
• Xiaomi reports a Q2 revenue of $12.46 billion, marking a 32% y
• Pavilion for Japanese Art Closed Temporarily
• Best headphones deal: Save $120 on Sony WH
• Xiaomi reports a Q2 revenue of $12.46 billion, marking a 32% y
• Arsenal vs. Barcelona 2025 livestream: Watch Women's Champions League final for free
• Roll Over, Pol Pot
• China calls on the Netherlands to uphold market principles amid new Dutch export controls on chip

• New Art Exhibit Features Heart Mountain Incarceree Joe Nakanishi
• Short Films by Sansei Directors to Be Shown at Union Church
• ‘We Are Stronger Together Than Apart’
• ‘Liz and the Blue Bird’ at Theaters Statewide
• Nebuta Returns to Hollywood Christmas Parade This Sunday
• Cementing Her Reputation
• Mochi Madness 2018
• ‘Strangers’ in the Night
• A Sansei Story
• OAA Holiday Boutique

• Roll Over, Pol Pot
• Northampton Saints vs. Union Bordeaux
• The 15 best new shows on Netflix
• Xpeng asks suppliers to step up production on strong demand for budget EV · TechNode
• 'We'll Be Rooting for You'
• Apple smart glasses could come as soon as 2026
• China calls on the Netherlands to uphold market principles amid new Dutch export controls on chip
• Chinese lidar maker Hesai says it could turn profitable by year end · TechNode
• Canine Cinema
• Chinese ride

• Хьюстон, мы вышли в открытый космос — как прошел финал Winline EPIC Standoff 2 Cosmo: Major
• Wait, Napster is back? Technically, yes.
• Xiaomi reports a Q2 revenue of $12.46 billion, marking a 32% y
• Kuaishou invites nine movie directors to produce clips using Kling model · TechNode
• Early Works of Seijun Suzuki at Egyptian Theatre
• What's new to streaming this week? (May 23, 2025)
• Alibaba yields “good results” from three
• 20% of NIO’s battery swap stations approach breakeven point · TechNode
• Hirahara to Discuss ‘Hiroshima Boy’ at JANM
• China’s MiniMax introduces company's first Sora