News for hackers. Stuff that matters.

A comment on Sora: Creating video from text. Parent comment

Re:Sora: Creating video from text by jsheard on Thursday February 15, 2024 @01:49PM (#39386699)
Where is the training material for this coming from? The only resource I can think of that's broad enough for a general purpose video model is YouTube, but I can't imagine Google would allow a third party to scrape all of YT without putting up a fight.
[ Parent | on HN ]
Re:Sora: Creating video from text by Zetobal on Thursday February 15, 2024 @01:56PM (#39386794)
It's movies the shots are way to deliberate to have random YouTube crap in the dataset.
[ Parent | on HN ]
Re:Sora: Creating video from text by cma on Thursday February 15, 2024 @03:55PM (#39388689)
You can still have a broad dataset and use RLHF to steer it more towards the aesthetic like midjourney and SDXL did through discord feedback. I think there was still some aesthetic selection in the dataset as well but it still included a lot of crap.
[ Parent | on HN ]