OpenAI has taken a major leap forward in AI creativity with the introduction of native image generation in its GPT-4o model. Announced on Tuesday, this update enables users to generate a diverse range of images—including infographics, comic strips, memes, street signs, and user interfaces—purely from text prompts. What sets this feature apart is its ability to refine and edit images through follow-up instructions, offering a more interactive and customisable creative experience.
Among its most viral applications is the ability to transform regular images into Studio Ghibli-inspired artwork. The beloved Japanese animation studio, known for its lush landscapes, soft colour palettes, and enchanting storytelling, has captivated audiences for decades with films like Spirited Away and My Neighbor Totoro. Now, with GPT-4o’s latest feature, users can upload any image and request a Ghibli-style reimagining, sparking an online frenzy.
Get Latest Mathrubhumi Updates in English
The internet goes Ghibli crazy
Dubbed “Images in ChatGPT,” this feature has taken social media by storm. Users have flooded platforms like X with their AI-generated Ghibli-style creations, turning everyday snapshots into dreamlike, hand-drawn masterpieces. From tranquil countryside scenes to whimsical cityscapes, the trend has particularly resonated with Studio Ghibli’s dedicated fanbase, who see it as a way to merge modern technology with timeless animation artistry.
The ability to seamlessly convert images into Ghibli-style artwork has ignited a new wave of creativity, showcasing how AI can be both a tool for artistic expression and a means of reinterpreting beloved visual aesthetics.
Even OpenAI CEO Sam Altman joins the fun
The excitement surrounding GPT-4o’s image generation hasn’t been limited to everyday users—even OpenAI CEO Sam Altman couldn’t resist the trend. He swapped his profile picture on X for a Ghibli-style portrait of himself and shared a humorous take on the phenomenon:
“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.’”
Altman’s lighthearted response highlights the widespread appeal and playful nature of the feature, even among OpenAI’s leadership.
Beyond DALL-E: A seamless AI art experience
Unlike previous AI-generated art, which relied on external tools like OpenAI’s DALL-E, GPT-4o’s native image generation integrates image creation directly within the model. This means users can craft visuals effortlessly, specifying details like aspect ratio, colour schemes (using hex codes), or even transparent backgrounds—all through simple text prompts.
For those who prefer it, DALL-E remains available as a standalone option, but GPT-4o’s ability to handle images within its chat-based framework marks a significant evolution in AI-powered creativity. As users continue to experiment with this new feature, it’s clear that OpenAI has unlocked a fresh era of AI-driven artistic expression.
