Re:Sora: Creating video from text
by nuz on Thursday February 15, 2024 @01:56PM
(#39386797)
I saw similar artifacts in dalle-1 a lot (as if the image was pasted onto geometry). Definitely wouldn't surprise me if they use synthetic rasterized data to in the training, which could totally create artifacts like this.
[ Parent
| on HN ]
There are no comments on this comment yet.