It's possible it was pre-trained on 3D renderings first, because it's easy to ge... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		spyder on Feb 15, 2024 \| parent \| context \| favorite \| on: Sora: Creating video from text It's possible it was pre-trained on 3D renderings first, because it's easy to get almost infinite synthetic data that way, and after that they continued the training on real videos.

iandanforth on Feb 16, 2024 [–]

In the car driving on the mountain road video you can see level-of-detail popping artifacts being reproduced, so I think that's a fair guess.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact