NVIDIA’s New AI: Text To Video Supercharged!

❤️ Check out Lambda here and sign up for their GPU Cloud:

📝 Magic 1-For-1:

📝 Phantom:

📝 Relighting paper:

📝 Stepfun:

📝 My paper on simulations that look almost like reality is available for free here:

Or this is the orig. Nature Physics link with clickable citations:

🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible:
Benji Rabhan, B Shang, Christian Ahlin, Gordon Child, John Le, Juan Benet, Kyle Davis, Loyal Alchemist, Lukas Biewald, Michael Tedder, Owen Skarpness, Richard Sundvall, Steef, Taras Bobrovytsky, Thomas Krcmar, Tybie Fitzhugh, Ueli GallizziIf you wish to appear here or pick up other perks, click here:

My research:
X/Twitter:
Thumbnail design: Felícia Zsolnai-Fehér –

Joe Lilli
 

  • @juliandarley says:

    extraordinary progress indeed. hopefully, soon characters’ actions will be a bit more varied and movement less restricted and actions will become more directable. i am pretty sure lots of brainpower (and AI power) is going into this!

  • @SPOOKEXE says:

    looks wicked, ill try it out after my model finishes training😁

  • @Napert says:

    2:26 so a 5090 or a h100, got it

  • @singularonaut says:

    Wow 😲

  • @DimitrisPotamianos says:

    like my comment plz

  • @Happy-vz3xe says:

    What a time to be alive

  • @Steamrick says:

    Hmm… looking at the magic 1-for-1 website, the output resolution of the sample videos is 640×368. That’s a bit on the low side.

  • >