Join our daily and weekly newsletter for the latest updates and exclusive content on industry-leading AI coverage. learn more
If you are on the internet (or at least on social network X) on the last day or so, you may encounter colorful, smooth anime-style images of famous photos in Japanese studio style, the studio Ghibli (a picture made) Princess Mononoke,,,,, Boy and craneand My neighbor Totoroin many other classic animated movies).
In fact, some users are complaining because their feeds seem to be filled with these types of images almost completely.
Is it true Current President Trumpthe iconic image of the “Tankman” during the 1989 Pro-Democracy Tiamman Square protest, Osama bin LadenJeffrey Epstein, and even other pop culture moments and characters Sam Rockwell’s iconic cameo White lotus and Many popular memespeople have been making and sharing these images in quick edits.
Powered by local image gen of the new GPT-4O model
This is largely thanks to Openai’s new update to the GPT-4O model for the Pro, Plus and Team subscription layers, which will turn on “Local Image Generation”.
While ChatGpt previously allowed users to create images from text prompts, it does this by routing it to another separate OpenAI model, DALL-E 3.
But OpenAI’s GPT-4O model is so named “O” because it’s a “Omni” model – the company trained it not only on text and code, but also on images and code, but on images and images and presumably on video and audio, which can make it understand all these forms of media and their similarity, but also on the results of “Apple” (both both apple and apple), rather than green things, can also draw a range of green, because it is certain, but certain, and so, and certain. Production media prompts for user given text prompts No Connect to any external model.
As a result, like a competitor Recent updates to Google AI Studio include Gemini 2.0 Flash Experimental Image Creation Modelthe new OpenAI GPT-4O can also accept image uploads for any pre-existing images in the camera volume, or uploads that you have recorded on the screen or saved from the network.
How to make a Ghibli-style image using Chatgpt (and change any image to any style!)
First, navigate to chat.com or chatgpt.com and make sure you are logged in with your Chatgpt Plus, Pro or Team account and the AI model selector (located in the left corner of the session window) will appear as “GPT-4O” (you can click it to click to drop it down and select the appropriate model among the available options).
After doing this, you can upload the image to chatpt using the “+” button in the lower left corner of the timely input text box, and now you can ask the new GPT-4O for the new GPT-4O with the image creation model to render your pre-existing image as a new style.
If you like, you can do this by uploading photos of yourself and friends and then typing “make all of these people try in the style of Ghibli animation.” In a few seconds, it will do it with some compelling and interesting results. It even supports connecting multiple images and combining them into a single piece.
chatgpt free use layer delay
Openai initially said that this will also enable this feature for free (Chatgpt’s no pay users), but unfortunately for them, co-founder and CEO Sam Altman released today that the feature will be delayed due to overwhelming demand from existing payment subscribers for Chatgpt Plus Plus, Plus, Pro and Team Tiers.
Like him Written on X:
“Images in Chatgpt are more popular than we expected (and we expected them to be high).
Unfortunately, the rollout to our free layer will be delayed for a while.“
Meanwhile, those who do have access to may continue to remove image editing in this and other recognizable or novel styles.
Of course, not everyone likes Openai’s works. In fact, Studio Ghibli creator Hayao Miyazaki himself appears in the documentary Back to 2016 – One of the most memorable moments still cited today is his overwhelming disgust and reaction to early examples of AI-driven animation and physics, which you guessed right, is an Openai model.
Like many generated AI products and services, this new image generation capability training data for OpenAI is still in the package, but is widely speculated to include copyrighted materials-and Imitation styles are not usually considered copyright infringement In the United States, it is rubbing some The original animation was in the wrong way.
For now, brands and businesses that want to use this style should be carefully considered and carefully given that some users may experience negative strikeback. But for those who have unabashed pro-Immortal tools or more tolerant and entertaining fan base, it’s clear that Openai has hit another blow.
Source link
