News for hackers. Stuff that matters.
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.

There are no comments on this comment yet.