AI Horizon

After only one day, OpenAI has put a halt on the free version of its in-app image generator, powered by the GPT-4o reasoning model. The update is intended to improve realism in images and text in AI-generated context; however, users have already created a runaway trend that has caused the AI company to rethink its rollout strategy. 

Not long after the update became available on ChatGPT, users began sharing images they had fashioned to social media platforms in the style of Studio Ghibli, the popular Japanese animation studio. Creations ranged from Studio Ghibli-based personal family photos to iconic scenes from the 2024 Paris Olympics, scenes from movies including “The Godfather” and “Star Wars”, and internet memes including distracted boyfriend and disaster girl.

While OpenAI CEO, Sam Altman, also joined in on the fun on Wednesday by changing his X profile picture to a Studio Ghibli style image of himself, which pundits assume was fashioned using GPT-4o, the executive also followed up with a prompt response, stating on the social media platform that the image generator update would be delayed for the ChatGPT free tier for the time being. He didn’t give any indication of whether or when the feature would return. Currently, paid tiers of ChatGPT, including Plus, Pro, and Team, still have access to the update. 

The Verge noted that the GPT-4o reasoning model uses a method called “autoregressive approach” to generate images, which develops the image from left to right and top to bottom, instead of all at once. This aids accuracy and realism when generating images. AI text on older models is known for being either blurry or gibberish, while GPT-4o text can generate sharp and coherent text. OpenAI also told the Wall Street Journal that it put the reasoning model through human-directed post-launch training to find common errors in text and image designs.

Ethics and legality is a long-standing issue when it comes to AI. While the brand attempted to cover its bases, divulging to the WSJ the sources of its data for training, it was impossible to know how the public will respond to the product once it’s available. 

Neal & McDevitt intellectual property lawyer Evan Brown told TechCrunch that ChatGPT users utilizing the GPT-4o-powered product to generate Studio Ghibli-style photos technically is not breaking the law because “style is not explicitly protected by copyright.” However, it does lie in a legally gray area. 

An OpenAI spokesperson also told the publication in a statement that ChatGPT can emulate a studio’s style, but not the style of an individual artist.

The AI company does seem to be aiming to cover its bases by removing the GPT-4o update from its ChatGPT free tier until it figures out its next move. 

There have been many AI trends based on popular designs. One older trend from late 2023 allowed users to generate Funko Pop! figures in Microsoft Designer with a few prompts. While the main premise of this trend was to make figures of yourself, many people made Funko Pop! figures of notable people, such as Elon Musk, and Beyonce. Similarly, this trend brought to light the legal restraints that can arise while trying to have fun with AI online. You had to input certain nickname workarounds, such as “Elon X” and “Queen Bey,” with proper descriptions of the characters to generate your desired results.