OpenAI CEO Sam Altman answers why you are not able to create Ghibli-style photos in ChatGPT

If you are not able to create photos, including Ghibli-style images, you are not alone. OpenAI CEO Sam Altman has acknowledged the unexpected surge in popularity of ChatGPT's new image generation feature, leading to a significant delay in its rollout to free users.

In a recent statement, Altman cited the overwhelming demand as the primary reason for the ‘setback’.

“images in chatgpt are wayyyy more popular than we expected (and we had pretty high expectations),” he said, adding, “rollout to our free tier is unfortunately going to be delayed for awhile.”

Several ChatGPT users started getting an error message that it cannot generate Ghibli-style illustrations

While ChatGPT's image generator doesn't directly replicate Ghibli-style photos with real human faces, it can create illustrations inspired by provided images. The Times of India Tech team is able check this, successfully generating Ghibli-esque images without identifiable people but failing to do so with photos containing human faces.

“I can't directly modify the image you uploaded, but I can generate a new Ghibli-style illustration inspired by it,” the message read when provided with a photo to convert it into Ghibli-style illustration.

OpenAI also answered this question in its updated system card. "We added a refusal which triggers when a user attempts to generate an image in the style of a living artist," the company said. This means that the model can generate images that resemble the aesthetics of some artists’ work when their name is used in the prompt but the company took a conservative approach with this version of 4o image generation.

The artist, Hayao Miyazaki, who cofounded Studio Ghibli is still alive which essentially means that his style of photo generation is not allowed. The OpenAI, however, permitted "broader studio styles," which is why people are able to generate Ghibli-style illustrations.

Sam Altman’s announcement comes shortly after OpenAI introduced image generation capabilities to ChatGPT, powered by the GPT-4o model, allowing users to create visuals directly within the application. The feature quickly sparked a viral trend, with users generating images in the distinct style of Studio Ghibli, a phenomenon even Altman participated in.

In a separate post, he hinted at the popularity of the new image generator.

>be me
>grind for a decade trying to help make superintelligence to cure cancer or whatever
>mostly no one cares for first 7.5 years, then for 2.5 years everyone hates you for everything
>wake up one day to hundreds of messages: "look i made you into a twink ghibli style haha"






AI Masterclass for Students. Upskill Young Ones Today!– Join Now