Eating the world, a terrifying concept, goes prime time as text to video shows why video's a resource hog to the max. Yours truly does video and files sizes of same are immense. Did one for my town. Raw content, try 38 gigs. Crunched, 5. Now have ChatGPT or Veo do the drill of making videos using text to replace a video editor like DaVinci in real time. Video file sizes are similar but eating the world applies even more because AI hoovers up energy resources to the max to produce the video in question, a process far more energy intensive than previously thought.
As detailed in a new paper, researchers from the open-source AI platform Hugging Face found that the energy demands of text-to-video generators quadruple when the length of a generated video doubles — indicating that the power required for increasingly sophisticated generations doesn’t scale linearly.
Endgame. Think of the energy requirements when the Veo's of the world do full length blockbusters
as this is going to happen because its cheaper.
as this is going to happen because its cheaper.

No comments:
Post a Comment