Image generation is now native to ChatGPT‑4o

OpenAI has levelled up image generation on ChatGPT with GPT-4o, bringing an easier, more streamlined way to create visuals. Rolling out to Plus, Pro, Team, and Free users, as well as developers via API, this update promises images that are “not only beautiful but useful.”

Unlike before—where ChatGPT relied on a separate model for visuals—GPT-4o now handles both text and image generation, meaning it pulls from its world knowledge and contextual smarts to craft images that feel more natural and intuitive in conversation, as per OpenAI. 

With text rendering, multi-turn generation, instruction following, and in-context learning, the model fine-tunes visuals with a refined style and photorealistic detail, backed by its deep world knowledge.

Every image comes stamped with C2PA metadata, an invisible watermark that logs its origins. And, while creativity is said to be the name of the game, OpenAI has guardrails in place— no violations of content policies, no explicit material, deepfake abuse, or graphic violence slipping through the cracks.

4o image generation rolls out starting March 24. It’s also available to use in Sora. For those who hold a special place in their hearts for Dall-e, it can still be accessed through a dedicated Dall-e.GPT.