ChatGPT’s Ghibli-style photo generating capabilities have taken the internet by storm. As more people experiment with this feature, ChatGPT-maker OpenAI’s CEO Sam Altman has a request for users. Taking to microblogging site X, Altman shared a post asking users to “chill” on generating Ghibli-style images. He wrote “can yall please chill on generating images this is insane our team needs sleep”. When a user replied “If you keep nerfing the model, people will stop using it. Otherwise, no”, the CEO said “we are gonna do the opposite of nerfing it BUT still please chill out a bit”
“Fire your team and generate a new team,” said another user, to which Altman replied “no thanks, in addition to building AGI this team is on trajectory to build the biggest website in the world from a cold start 2.33 years ago, best team in the world, it’s just hard”.
How to create Ghibli-style Portraits without ChatGPT Plus
AI models like Google’s Gemini or Grok can also create Studio Ghibli-style visuals—think lush greenery, soft lighting, and expressive characters—provided you’re precise with your prompts, such as “a serene Ghibli-style girl with flowing hair under a cherry blossom tree.”
However, the output might differ from ChatGPT’s GPT-4o creations, as each model interprets styles uniquely due to differences in training data and algorithms. While ChatGPT’s images lean toward photorealistic finesse, Gemini, Grok by Elon Musk-owned AI company xAI — available through X, or trial-based platforms might produce a slightly more abstract or varied take on Ghibli’s charm, requiring some experimentation to nail the vibe.
Free platforms like Craiyon, DeepAI, and Playground AI offer AI image generation with varying levels of customization. Simply upload a photo or type a prompt like “portrait in Studio Ghibli style, lush forest background, soft colors,” and let the AI work its magic.
Again, these tools may not match GPT-4o’s photorealistic precision, but they can mimic Ghibli’s whimsical aesthetic.
