Comment on OpenAI introduces Sora, its text-to-video AI model
draxil@lemmy.world 8 months agoThis would be the most GPU intensive compression algorithm of all time :)
Comment on OpenAI introduces Sora, its text-to-video AI model
draxil@lemmy.world 8 months agoThis would be the most GPU intensive compression algorithm of all time :)
lea@feddit.de 8 months 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.