Re:Sora: Creating video from text
by supriyo-biswas on Thursday February 15, 2024 @01:28PM
(#39386340)
I wonder what served as the dataset for the model. Videos on YouTube presumably, since messing around with the film industry would be too expensive?
[ Parent
| on HN ]
Almost certainly troves of stock footage. The type of exaggerated motion seen in these examples is very reminiscent of stock footage. And it is heavily textually annotated for search.
How would they access youtube tough?