An anonymous reader quotes a report from Ars Technica: On Monday, Toys "R" Us announced that it had partnered with an ad agency called Native Foreign to create what it calls "the first-ever brand film using OpenAI's new text-to-video tool, Sora." OpenAI debuted Sora in February, but the video synthe...
Video source for those who don’t feel like clicking around.
They don’t go into detail, but I’d be real interested to see a breakdown of how this was made. It looks almost entirely like actual Sora output, with the exception of Geoffrey and the TRU logo, which I think are comped-in renders. But the rest of it all looks like genuine AI output, all the way down to a bit of R’lyehian text in a few places.
It’s honestly a little scary how good this looks. Granted, this was made by a professional media team who understand how these tools work and know how to use them better than anyone else, so of course it’s going to be good. But it won’t be long at all before this becomes the baseline.
Video source for those who don’t feel like clicking around.
They don’t go into detail, but I’d be real interested to see a breakdown of how this was made. It looks almost entirely like actual Sora output, with the exception of Geoffrey and the TRU logo, which I think are comped-in renders. But the rest of it all looks like genuine AI output, all the way down to a bit of R’lyehian text in a few places.
It’s honestly a little scary how good this looks. Granted, this was made by a professional media team who understand how these tools work and know how to use them better than anyone else, so of course it’s going to be good. But it won’t be long at all before this becomes the baseline.