As AI tools emerge, journalists will play an increasingly vital role in helping people distinguish quality from the noise. Writing for tom’s guide, Ryan Morrison has reviewed seven image generators to determine which is the most effective at creating a photorealistic image of a woman from a text prompt. To my eyes, with the exception of DALL-E, they all produced a result that could be mistaken for a real photo. Describing the differences in the models’ capabilities, Morrison wrote:

Well, the underlying technology is fairly mature. There are still strong distinctions between one model and the next and even the way one company might deploy the same version of a model in a completely different way to another company.

In some areas, there’s a lot of convergence particularly around hyperrealistic human faces but in others, there are distinct differences especially in things like text rendering skin texture and prompt following.

… When it comes to rendering individuals using AI it is clear the top models are starting to converge, with very similar-looking characters appearing from the same prompt across different tools. The ability to render text is still variable with only Ideogram largely consistent.