OpenAI upgraded
ChatGPT-4o with advanced image generation capabilities on Wednesday. With the launch of its new native image creation feature, called ‘4o Image Generation’, the US-based artificial intelligence (AI) research company has sparked an online frenzy.
Soon after its release, users on social media discovered the tool’s remarkable ability to replicate various artistic styles, including transforming photos into legendary Studio Ghibli's animation aesthetic. Subscribers to ChatGPT Plus, Pro, and Team have flooded platforms X and Instagram with ChatGPT-powered Ghibli-esque pictures.
OpenAI chief executive Sam Altman also joined the trend by updating his profile picture on X to a Studio Ghibli-style image and inviting users to generate an improved version for him using ChatGPT. “Be me. Grind for a decade trying to help make superintelligence to cure cancer or whatever. Mostly no one cares for the 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,” said Altman in a post on
X.
What is Studio Ghibli?
In the whimsical world of animation, few names command as much admiration as Studio Ghibli. Founded in 1985 by legendary directors Hayao Miyazaki, Isao Takahata, and producer Toshio Suzuki, Studio Ghibli is an animation studio that captivated fans worldwide with its visuals, and storytelling. Known for movies Spirited Away (2001), My Neighbor Totoro (1988), and Howl’s Moving Castle (2004), the studio has received global recognition, including an Academy Award for Best Animated Feature.
Although Studio Ghibli has not yet commented on the use of its distinctive art style by OpenAI, Miyazaki had earlier strongly criticised AI-generated animation. According to media reports, in a 2016 interview, Miyazaki describing it as “an insult to life itself”.
“I cannot watch this and find it interesting. Those who create such things have no understanding of pain. I am completely disgusted. If someone wishes to make unsettling content, they are free to do so, but I would never consider incorporating this technology into my work. I firmly believe it is an insult to life itself,” he said.
How does OpenAI's new image generation tool work?
Unlike earlier AI-generated art that depended on external tools such as OpenAI’s DALL-E, ChatGPT-4o’s new feature is a built-in image generator. Simply by putting in text prompts, the feature allows users to create visuals seamlessly within the model itself. Users can specify attributes such as aspect ratio, colour schemes using hex codes, or opt for transparent backgrounds with ease.
According to OpenAI, ChatGPT‑4o can also analyse and learn from user-uploaded images, seamlessly integrating their details into its context to inform image generation.
“We trained our models on the joint distribution of online images and text, learning not just how images relate to language, but how they relate to each other,” OpenAI said in a blog post.
According to OpenAI, GPT‑4o image generation excels at accurately rendering text, precisely following prompts, and leveraging 4o’s inherent knowledge base and chat context—including transforming uploaded images or using them as visual inspiration. “These capabilities make it easier to create exactly the image you envision, helping you communicate more effectively through visuals and advancing image generation into a practical tool with precision and power,” the blog post reads.
OpenAI stated that it will “block requests for generated images that may violate our content policies, such as child sexual abuse materials and sexual deepfakes”.
Beyond Studio Ghilbhi
While transforming photos into Studio Ghilbhi style images has become its viral application, the versatile image generation tool lets users explore creativity across various artistic domains, such as South Park, Minecraft, Lego, voxel, watercolour, marionette, and rubber hose animation. It also supports creative design applications, particularly in producing infographics, product mockups, logos, posters, and other visual advertising campaigns.
ChatGPT’s new AI image feature rollout delayed for free users
According to Altman, the release for free users would be postponed due to the feature's unforeseen success.
Acknowledging the success of the tool, Altman said on X, “Images in chatgpt are wayyyy more popular than we expected (and we had pretty high expectations). Rollout to our free tier is unfortunately going to be delayed for a while.”
The company said it will be rolling it out to Enterprise and Edu users via its API soon.
Here’s a look at the CHatGPT-triggered Ghibli fest on social media: