Author: 0xFacai, Rhythm BlockBeats
Original Title: “$Ghibli Soars 100 Times in Half a Day, New Features of GPT-4o Ignite ‘Hayao Miyazaki Style’ Across the Internet”
From last night to this morning, a flood of meme images reminiscent of Hayao Miyazaki’s cinematic style suddenly appeared on various social media platforms, such as the popular “Super Universal” meme below, which has gained a new charm and vitality under the “Ghibli Style” rendering.
Of course, some classic anime scenes also made their way into this “remake feast,” morphing into hellish jokes like “Thanks, Vance,” and “Airplanes crashing into buildings…”
At the same time, a meme coin named $Ghibli has also entered rapid mode on the blockchain, soaring in value since its launch at 6 PM yesterday. Under the hype this morning, its market capitalization skyrocketed, surpassing $24 million at the time of writing, with a 24-hour increase exceeding 10,824%.
What Happened? What is Ghibli?
All of this can undoubtedly be attributed to the newly launched features of GPT-4o. On Tuesday, OpenAI activated the built-in image generator of GPT-4o, which is dubbed by the company as “the most advanced image generator to date,” boasting the capability of “precise, accurate, and realistic outputs through its local multimodality.” It was discovered that this image generator is particularly adept at replicating the anime style of Studio Ghibli.
On Wednesday, OpenAI’s CEO Sam Altman was the first to kick off this wave of “Ghibli virus propagation” on X, even changing his profile picture to an image styled in the Ghibli fashion.
Subsequently, many Twitter celebrities began to follow suit, uploading their images rendered in Ghibli style. Even Musk, the founder of Grok AI, OpenAI’s rival, commented in his “image tweet”: “This is today’s theme.”
While ChatGPT previously allowed users to create images from text prompts, it did so by routing them to another separate OpenAI model, DALL-E 3. The reason the GPT-4o model is named “O” is that it is an “Omni” model. This means that, in addition to text coding, OpenAI has also trained it on image codes and even audio and video, enabling it to understand all these forms of media and their similarities, generating the requested media based on user prompts without needing to connect to any external models.
Recently, AI giants have been engaged in fierce competition over image creation models, with Google also recently updating its experimental image creation model, Gemini 2.0 Flash. Clearly, having AI serve as a personal artist to create images that fully understand your meaning is becoming an increasingly simple task.
Hayao Miyazaki, co-founder of Studio Ghibli, has previously expressed strong opposition to AI-generated animation. At a conference in 2016, he stated regarding AI animation: “I feel completely disgusted. If you really want to create something creepy, you may continue. I never want to incorporate this technology into my work,” adding that he sees it as “an insult to life itself.”
How to Create Your Own Ghibli?
First, navigate to chat.com or chatgpt.com, and ensure you are using a GPT Plus, Pro, or Team account, with the AI model selector showing “GPT-4o.” Use the “+” button in the lower-left corner of the real-time input textbox to upload an image, then tell the new GPT-4o with the image creation model to “Redraw this image in Ghibli animation style.” You can also upload multiple images and combine them into one with the Ghibli style. In short, try as much as possible; GPT-4o will surprise you.
Of course, the meme token $Ghibli merely combines the artistic aesthetics of Studio Ghibli with the trend of AI-generated content in its narrative, which is why it rapidly gained attention on Twitter. However, the information behind the token’s team is currently unclear, and investors should approach the corresponding risks with caution.
This article is reprinted with permission from Rhythm BlockBeats.