After a short delay, OpenAI has begun rolling out ChatGPT’s built-in image generation feature to free users. Although neither OpenAI nor its CEO, Sam Altman, has officially confirmed the rollout, tests conducted using multiple free ChatGPT accounts have successfully generated Studio Ghibli-style images without any issues. This suggests that the feature is now available to free users.

Previously, OpenAI introduced the native image generation feature for all ChatGPT Plus, Pro, and Team users worldwide on March 26. Following this release, many social media users became fascinated with Studio Ghibli’s artwork and started transforming their images into anime-style visuals inspired by the famous Japanese studio’s films. However, free users did not have access to this feature at first. As a result, they had to rely on alternatives such as xAI’s Grok chatbot or Google’s Gemini. While these alternatives provided similar functionality, the quality and level of detail in their generated images were not as refined as those produced by OpenAI’s model.

To create a Studio Ghibli-style AI image using ChatGPT, users need to visit the ChatGPT website or open the app. Once there, they can upload an image by clicking on the ‘+’ icon at the bottom left corner. After the image is uploaded, entering a command like “Ghiblify this” or “Turn this image into a Studio Ghibli theme” will prompt ChatGPT to generate the desired anime-style image. Users can then download and save the image for further use.

Although OpenAI did not specify any limitations on native image generation when the feature was first introduced, restrictions were later added due to excessive demand. CEO Sam Altman revealed that the overwhelming number of requests was putting immense pressure on the company’s GPUs. According to OpenAI’s latest update on X, formerly known as Twitter, free users can now generate up to three images per day.

This is not the first time ChatGPT has offered image generation capabilities. However, the major breakthrough lies in its newly acquired native image generation ability. Unlike previous iterations, where the chatbot relied on external tools like DALL-E 3, native image generation enables ChatGPT to create and edit images directly within its multimodal framework. This allows for smoother and more integrated image processing. While Google’s Gemini introduced native image generation earlier, ChatGPT has gained greater traction among users.

The introduction of native image generation is a significant milestone for OpenAI. By integrating this feature into GPT-4o, the chatbot can now refine images through natural conversation, giving users greater flexibility and control over their creations. It is also capable of handling multiple objects in an image, ranging from ten to twenty elements, ensuring more consistency and precision. Additionally, the ability to connect ChatGPT’s extensive text-based knowledge with image generation enhances the accuracy and contextual relevance of the generated visuals. This advancement marks a major step forward in AI-powered creativity and user interaction.

Disclaimer: This image is taken from Mint.