OpenAI has introduced a groundbreaking update to ChatGPT-4o, integrating a native image generation tool known as 4o Image Generation. The launch has triggered an online frenzy, with users quickly exploring its ability to mimic various artistic styles, particularly the legendary animation aesthetic of Studio Ghibli. Following the release, social media platforms such as X and Instagram were flooded with Ghibli-style AI-generated images, shared by subscribers of ChatGPT Plus, Pro, and Team. OpenAI’s announcement described the new tool as the most advanced image generator yet, featuring a multimodal model capable of producing highly precise, realistic, and stylistically accurate visuals.

CEO Sam Altman also joined the trend, updating his X profile picture with a Ghibli-inspired version of himself. He later humorously reflected on the situation, joking that after years of hard work on AI advancements, the most viral moment for him turned out to be users transforming his image into a Ghibli-style "twink."

Studio Ghibli and Miyazaki’s Criticism of AI: tudio Ghibli, founded in 1985 by Hayao Miyazaki, Isao Takahata, and Toshio Suzuki, is renowned for its visually stunning and emotionally rich animated films, including Spirited Away, My Neighbor Totoro, and Howl’s Moving Castle. The studio has received numerous international accolades, including an Academy Award for Best Animated Feature.

Despite the excitement surrounding AI-generated Ghibli-style images, Studio Ghibli has not officially commented on OpenAI’s new tool. However, Miyazaki has been a vocal critic of AI in animation. In a 2016 interview, he harshly condemned AI-generated visuals, calling them “an insult to life itself.” He expressed his disapproval by stating that those creating such technologies lack an understanding of pain and human emotion, making the concept deeply unsettling to him.

How OpenAI’s Image Generator Works: Unlike previous AI-generated art that relied on external tools like DALL-E, ChatGPT-4o’s new feature is fully integrated into the chatbot. Users can input text prompts to generate images seamlessly within the conversation. The tool allows for customization, including adjustments to aspect ratio, color schemes, and transparent backgrounds. It can also analyze user-uploaded images, incorporating details to refine and enhance its outputs.

OpenAI highlighted the technical advancements of the new generator, noting that it is capable of accurate text rendering, precise prompt-following, and contextual learning from uploaded images. The company also emphasized its commitment to responsible AI use, ensuring that content moderation mechanisms are in place to prevent the generation of explicit or harmful images.

Beyond Ghibli: Expanding Creative Possibilities: While the viral trend has focused on Ghibli-style artwork, the tool’s capabilities extend far beyond. Users have experimented with recreating images in diverse artistic styles, including South Park, Minecraft, Lego, voxel art, watercolor, marionette animation, and rubber hose animation. The tool is also proving valuable in graphic design, aiding in the creation of infographics, product mockups, logos, posters, and digital advertising visuals.

Delays in Rollout for Free Users: Due to overwhelming demand, OpenAI announced that the rollout of the image generator for free-tier users would be delayed. Altman acknowledged the unexpected surge in popularity, stating that the feature’s success had exceeded even their high expectations. He reassured users that OpenAI is working on expanding access and that the feature will soon be available for Enterprise and Education users through its API.

Disclaimer: This image is taken from X.