Soon, ChatGPT will generate images natively using OpenAI's GPT-4o AI model

Native text-to-image generation feature in ChatGPT will replace OpenAI's another dedicated image generation product named DALL-E it integrated into ChatGPT initially

OpenAI has announced that it is bringing native text-to-image generation capabilities to ChatGPT through its GPT-4o model. Initially, image generation was taken care of by another of OpenAI’s products named DALL-E. During a livestream on Tuesday, OpenAI CEO Sam Altman announced this first major update of ChatGPT this year. ChatGPT will now be able to leverage the GPT-4o model to natively create and modify images and photos.

 

OpenAI, in a statement to the Wall Street Journal, said that this new image-generation feature was made possible by training GPT-4o on “publicly available data” along with proprietary data from its partnerships with companies like Shutterstock.

 

Image generation in ChatGPT: What to expect

 

GPT-4o is a multimodal AI model capable of editing existing images, including images with people in them — transforming them or “inpainting” details like foreground and background objects. OpenAI in a blog post said that GPT??'4o’s image generation follows detailed prompts with attention to detail and can handle up to 10-20 different objects, whereas other systems start struggling after just 5-8 objects.

“GPT??'4o image generation excels at accurately rendering text, precisely following prompts, and leveraging 4o’s inherent knowledge base and chat context—including transforming uploaded images or using them as visual inspiration. These capabilities make it easier to create exactly the image you envision, helping you communicate more effectively through visuals and advancing image generation into a practical tool with precision and power,” said OpenAI.

 

The Sam Altman-led company also showcased several examples where GPT-4o excelled at the creation of images based on text prompts.

 

Altman announced that GPT-4o’s native image generation is officially live now for ChatGPT and Sora — OpenAI’s AI-powered video creation tool — but only for those on the $200-per-month Pro plan. OpenAI also mentioned that the feature will be making its way to ChatGPT Plus and free users soon, along with developers tapping into the platform through its API.