OpenAI has once again outpaced its competitors with the rollout of its most advanced image generator yet—GPT-4o. The new model excels in rendering text accurately, adhering closely to user prompts, and leveraging its vast knowledge base and chat context. It can even transform uploaded images or use them as visual inspiration, making it a powerful tool for creative and professional use.
Initially launched on March 25 for Plus and Pro subscribers, the feature has now been extended to free users, as announced by OpenAI CEO Sam Altman in an X post.
ChatGPT image gen now rolled out to all free users!” Altman stated, adding, Images in ChatGPT are wayyyy more popular than we expected,”which temporarily overwhelmed OpenAI’s GPUs due to high demand.
A New Era of AI-Generated Art
The new image generator has sparked a wave of creativity, with users transforming their photos into stunning artworks—particularly in the beloved Studio Ghibli-style. These AI-generated portraits have taken social media by storm, showcasing the model’s ability to handle complex scenes with up to 10-20 different objects, far surpassing previous systems that struggled with just 5-8 objects.
How to Create Ghibli-Style Portraits
For those looking to experiment, detailed prompts with a focus on style and aesthetics yield the best results. GPT-4o’s ability to tightly bind objects with their traits and relationships allows for greater precision, making it easier than ever to bring imaginative visuals to life.
