FrontierThe story, in brief
Addendum to GPT-4o System Card: 4o image generation
OpenAI's GPT-4o now generates photorealistic images and takes images as input—a significant capability jump from DALL·E 3.
The KeyNews take
Why it matters
OpenAI is expanding GPT-4o's multimodal reach beyond text and vision-understanding into generative image creation, directly challenging specialized image models and expanding the moat of its flagship model.
The key facts
5 to knowGPT-4o image generation described as 'significantly more capable' than DALL·E 3
Can generate photorealistic output
Can take images as inputs and transform them
Published as system card addendum (indicates recent/imminent release)
Multimodal capability expansion of GPT-4o
Go to the source
OpenAI Blogopenai.com
Publisher excerpt: 4o image generation is a new, significantly more capable image generation approach than our earlier DALL·E 3 series of models. It can create photorealistic output. It can take images as inputs and transform them.