OpenAI announces native image generation in ChatGPT and Sora
OpenAI announced native image generation within ChatGPT. Here are the details.
OpenAI has native image generation in ChatGPT and Sora.
In a livestream led by CEO Sam Altman as well as members of OpenAI team, the company demoed new capabilities in image generation that's driven by the GPT-4o model.
Previously, image generation was powered by DALL-E and largely existed in a separate app that users had to switch over to. Now, that image generation is native to the ChatGPT app, the model's responses will understand contextual prompts without specific reference to an image, can follow prompts for reiterating on a generated image, and is better at rendering text according to the company.
With image generation in ChatGPT, OpenAI's goal is to make it more useful rather than just a novelty. That means it can generate diagrams, infographics, logos, social media posts, and other graphics.
Altman also said that the model leans into "creative freedom," saying "what we'd like is for the model to not be offensive if you don't want it to be, but if you want it to be within reason, really let people create what they want."
Native image generation for ChatGPT is available today for ChatGPT Plus, Pro, Team, and Free users within the chat experience, with access rolling out to Enterprise and Edu users soon.
