New Delhi: OpenAI has recently rolled out Images in ChatGPT, which is going to be powered by GPT Image 1.5, its flagship image generation model. It’s 4x faster and makes precise edits while keeping the likeness consistent across multiple generations. Additionally, it’s much better at following instructions; users can either generate images from scratch or upload an image and make edits inside the ChatGPT. OpenAI has also replaced the Library section in ChatGPT with the latest Images section, which can be accessed from the left sidebar. Users can try the latest styles, find inspiration to create the latest images, and find their library of generated images.
From Dramatic to Plushie, Doodle, holiday portrait, etc., users can find many different styles here. As for the image editing, OpenAI has stated that the latest AI model will follow the user’s intent more closely and keep people’s appearance consistent across multiple edits. In terms of creativity, too, the newest image model in ChatGPT is competent; it can generate movie posters, create ads in different styles, dress up characters, and much more. Next, users can create images with accurate text with the latest model in ChatGPT.
It is now capable of rendering denser and smaller text as well. Users can now reliably use it to create infographics, explainer graphics and more. After Google launched its most popular Nano Banana in Gemini, which generates incredible images, OpenAI has now come up with a more advanced model to compete with the latest Nano Banana Pro model. OpenAI’s GPT Image 1.5 has outranked Google’s Nano Banana Pro in both AI image generation and editing. The latest ChatGPT image model is rolling out to all of the users, including Free, Go, Plus, Edu and Pro Plans.
