Sam Altman, co-founder and CEO of OpenAI, speaks during the New York Times annual DealBook Summit at Jazz at Lincoln Center in New York City on Dec. 4, 2024.
Michael M. Santiago | Getty Images
OpenAI CEO Sam Altman on Thursday announced that viral use of ChatGPT’s new image-generation AI, introduced earlier this week, is overloading the company’s servers.
While it is “super fun seeing people love images” in ChatGPT, “our GPUs are melting,” Altman posted on social media site X on Thursday, adding that the company will temporarily limit the feature’s usage as it works to make it more efficient.
The rate limits affect OpenAI’s Tuesday debut of native image generation within ChatGPT. The company debuted the “high-quality” image-generation tool as a way to produce everything from diagrams, infographics and logos to business cards and stock photos. The feature can also use an image as a starting point for art, such as a custom painting of a pet or editing a professional headshot.
The image-generation feature began rolling out to ChatGPT PLUS, Pro and Team users on Tuesday, as well as users of the chatbot’s free tier when they use OpenAI’s 4o model. ChatGPT Enterprise and Edu users will receive access next week, the company said.
Images of anime-style renderings of users’ uploaded photos have been going viral on X and other social media apps since the feature’s Tuesday launch. Altman, for example, changed his X profile photo to an image generated by the new feature.
One of the company’s first hit products was the Dall-E model launched in 2021. That was one of the first artificial intelligence image generators, and was integrated into ChatGPT in 2023.
Users of ChatGPT’s free tier will soon be able to generate three images per day, Altman wrote.
— CNBC’s Kif Leswing contributed to this report.
WATCH: OpenAI expects revenue to triple to $12.7 billion this year
