After a brief delay, OpenAI finally seems to be rolling out ChatGPT’s native image generation feature to free users. While OpenAI or its CEO Sam Altman have yet to officially announce whether the feature has been rolled out to free users, we have tried to ‘Ghiblify’ a few images using several free ChatGPT accounts where the feature worked without a glitch.

OpenAI had rolled out the native image generation feature to all ChatGPT Plus, Pro and Team users worldwide on 26 March. Following this, social media users took a liking to the artwork of Japan’s Studio Ghibli and began turning their images into their real life pictures in the format of popular anime films.

However, as free users didn’t have access to this feature, they had to use alternatives such as xAI’s Grok chatbot or Gemini, which did the job, but the resulting images weren’t as detailed as the OpenAI model.

Here’s a look at few Ghibli style AI images we generated using ChatGPT.

Ghibli style image generated using ChatGPT free tier

Ghibli styled image generated using ChatGPT free tier

1) Head over to the ChatGPT website or app

2) Upload your image by clicking on the ‘+’ sign at the bottom left corner

3) Enter the text ‘Ghiblify this’ or ‘turn this image in Studio Ghibli theme’

4) You should get the desired image in Studio Ghibli style. Click on the download option to save it.

While OpenAI did not talk about a limit on native image generation during the rollout, the company later added restrictions on image generation for paid as well as free users owing to the excessive demand which CEO Sam Altman said was ‘melting’ their GPUs.

As of OpenAI’s last update on X (formerly Twitter), ChatGPT free users will be entitled for up to three image generations per day.

This is not the first time that ChatGPT has been able to generate images. In fact, the chatbot has been offering these services even to free users for a while now, but the real catch is the native image generation capability that it has now acquired.

What exactly is native image generation? Native image generation refers to the chatbot’s ability to generate and edit images directly using its multimodal capabilities rather than relying on external models like DALL-E 3. While Gemini introduced native image generation support earlier than ChatGPT, OpenAI’s chatbot has definitely gained better traction among the masses.

OpenAI has unlocked image generation capabilities directly in GPT-4o, allowing the chatbot to “refine images through natural conversation”. ChatGPT can now also handle between 10-20 different objects in an image, which brings more control and consistency to the images.

Native image generation can also connect ChatGPT’s text knowledge base with images, resulting in the chatbot generating more efficient and intelligent responses.