6 comments

  • Jaxkr 1 hour ago
    This guy is a genius; for those who don’t know he also brought us ControlNet.

    This is the first decent video generation model that runs on consumer hardware. Big deal and I expect ControlNet pose support soon too.

    • msp26 6 minutes ago
      I haven't bothered with video gen because I'm too impatient but isn't Wan pretty good too on regular hardware?
  • IshKebab 1 hour ago
    Funny how it really wants people to dance. Even the guy sitting down for an interview just starts dancing sitting down.
    • Jaxkr 36 minutes ago
      Massive open TikTok training set lots of video researchers use
  • ZeroCool2u 2 hours ago
    Wow, the examples are fairly impressive and the resources used to create them are practically trivial. Seems like inference can be run on previous generation consumer hardware. I'd like to see throughput stats for inference on a 5090 too at some point.
  • WithinReason 44 minutes ago
    Could you do this spatially as well? E.g. generate the image top-down instead of all at once
  • modeless 36 minutes ago
    Could this be used for video interpolation instead of extrapolation?
    • yorwba 5 minutes ago
      Their "inverted anti-drifting" basically amounts to first extrapolating a lot and then interpolating backwards.
  • fregocap 1 hour ago
    looks like the only motion it can do...is to dance