Apple’s patent 11475608 is for “Face Image Generation with Pose and Expression Control” which the Tame Apple Press thinks will be folded into a new tool for creating synthetic media.
The patent describes how Apple can apply AI to a reference image to adjust a human face’s expression and bearing in subtle and overt ways. The picture of a smiling person could become a photo of someone frowning or sticking their tongue out.
The idea is that it can be used to produce enough images strung together to mimic someone talking in a film. The only difference between what is out there now and Apple’s product is that its patent changes and alters an existing image, but doesn’t produce the images from scratch in the way OpenAI’s DALL-E, Midjourney, and other platforms operate. Like those tools, however, the manipulated image is not an actual photograph.
“At inference time, a single reference image can generate an image that looks like the person (i.e., the subject) of the reference image but shows the face of the subject according to an expression and/or pose that the system or method has not previously seen,” the patent said.
“Thus, the generated image is a simulated image that appears to depict the subject of the reference image, but it is not a real image.”
The Tame Apple Press is sure that there is nothing sinister in the technology, otherwise it would not be made by its favourite company.
Patently Apple said: "It's clear that Apple could take this technology much further if they so choose. It'll be interesting to see how Apple will make deepfake manipulation a friendly and non-threatening application."