Given that video is no more than a series of related images, this isn't as big a leap as you might think, though it no doubt requires a lot more computing power (as video does generally). Still, it shows how rapidly AI is moving into the creative space. "Meta revealed its new text-to-video tool yesterday (29 September) with a cutesy clip of a teddy bear painting a self-portrait on a canvas. The text prompt used was 'a teddy bear painting a portrait'." Of course, this might all be a sham. Would we expect anything less from Facebook? "As The Verge pointed out, Meta is not currently allowing anyone access to the model."
Today: 6 Total: 92 [Direct link] [Share]
