425
OpenAI introduces Sora, its text-to-video AI model (www.theverge.com)
submitted 2 years ago* (last edited 2 years ago) by to c/technology@lemmy.world
141 comments fedilink hide all child comments
 

https://openai.com/sora

Archive https://archive.is/V8Fv3

you are viewing a single comment's thread
view the rest of the comments
[–] 51 points 2 years ago (1 child)

This would be the most GPU intensive compression algorithm of all time :)

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •
  • [–] 18 points 2 years ago

    And the largest ever decoder since it'll need the whole model to work. I'm not particularly knowledgeable on AI but I'll assume this will occupy hundreds of gigabytes, correct me if I'm wrong there. In comparison, libdav1d, an av1 decoder, weighs less than 2 MB.

  • permalink
  • fedilink
  • source
  • parent