Author: Blockbeats
Reprint: Lawrence, Mars Finance
From last night until this morning, a large number of meme images resembling the style of Hayao Miyazaki's film works suddenly emerged on social media platforms like X, such as the still-popular 'Super Generic' meme, which, under the 'Ghibli style' rendering, takes on a new charm and vitality.
Of course, some classic old anime and famous scenes also appeared in this 'remake feast,' turning into hellish jokes like 'Vans should thank you' and 'airplanes crashing into buildings'...
Meanwhile, a meme coin named $Ghibli has also started a fast track mode on the blockchain, beginning to rise since its issuance at 6 PM yesterday afternoon, and amid the hype this morning, its market value has soared to over $24 million, with a 24-hour increase of over 10,824%.
What happened? What is Ghibli?
Of course, all of this is thanks to the freshly launched new feature of GPT-4o.
On Tuesday, OpenAI launched the built-in image generator of GPT-4o, which is officially called 'the most advanced image generator to date' and has the capability of 'precise, accurate, and realistic outputs with native multi-models.' People have found that this image generator is especially good at replicating the anime style of Studio Ghibli, created by Hayao Miyazaki.
In a tweet on Wednesday, OpenAI's CEO Sam Altman initiated the 'Ghibli viral spread' and even changed his avatar to an image in Ghibli style.
Subsequently, many Twitter celebrities also began to follow suit, uploading their images rendered in Ghibli style. Even Elon Musk, the founder of Grok AI, OpenAI's competitor, wrote in his 'image tweet': This is today's theme.
Although 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 why the GPT-4o model is named 'O' is that it is an 'Omni' model. This means that OpenAI has trained it not only on text code but also on image code and even audio and video, enabling it to understand all these forms of media and their similarities, and to generate the given media based on user prompts without connecting to any external models.
Recently, AI giants are in fierce competition over image creation models, and Google has also recently updated its experimental image creation model Gemini 2.0 Flash. Clearly, having AI as your personal artist to create an image that fully understands your meaning is becoming very simple.
Studio Ghibli's co-founder Hayao Miyazaki has previously expressed strong opposition to AI-generated animation. At a conference in 2016, Miyazaki stated about AI animation: 'I feel completely disgusted. If you really want to create something creepy, you can go ahead. I never want to incorporate this technology into my work,' and added that it is 'an insult to life itself.'
How to generate your own Ghibli?
First, navigate to chat.com or chatgpt.com, and ensure that you are using a GPT Plus, Pro, or Team account, with the AI model selector showing 'GPT-4o.'
Use the '+' button in the bottom left corner of the input text box to upload an image, and then you can tell the new GPT-4o with image creation model to 'redraw this image in the style of Ghibli animation.' You can also upload multiple images and combine them into one image in Ghibli style. In short, do try it out; 4o will surprise you.
Of course, the related meme token $Ghibli has merely combined the artistic aesthetics of Studio Ghibli and the trend of AI-generated content in its narrative, which is why it quickly went viral on Twitter. However, the information about the team behind the token is currently unclear, and investors should be cautious about the associated risks.