Packing Input Frame Context in Next-Frame Prediction Models for Video Generation
lllyasviel.github.io
Packing Input Frame Context in Next-Frame Prediction Models for Video Generation
1–10 of 29 posts
Re: Packing Input Frame Context in Next-Frame Prediction Models for Video Generation
#2Wow, 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.
Re: Packing Input Frame Context in Next-Frame Prediction Models for Video Generation
#3This 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.
Re: Packing Input Frame Context in Next-Frame Prediction Models for Video Generation
#4Funny how it really wants people to dance. Even the guy sitting down for an interview just starts dancing sitting down.
Re: Packing Input Frame Context in Next-Frame Prediction Models for Video Generation
#5looks like the only motion it can do...is to dance
Re: Packing Input Frame Context in Next-Frame Prediction Models for Video Generation
#6Could you do this spatially as well? E.g. generate the image top-down instead of all at once
Re: Packing Input Frame Context in Next-Frame Prediction Models for Video Generation
#7Could this be used for video interpolation instead of extrapolation?
Re: Packing Input Frame Context in Next-Frame Prediction Models for Video Generation
#8Funny how it really wants people to dance. Even the guy sitting down for an interview just starts dancing sitting down.
Massive open TikTok training set lots of video researchers use
Re: Packing Input Frame Context in Next-Frame Prediction Models for Video Generation
#9Could you do this spatially as well? E.g. generate the image top-down instead of all at once
[dead]
Re: Packing Input Frame Context in Next-Frame Prediction Models for Video Generation
#10This 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.
I haven't bothered with video gen because I'm too impatient but isn't Wan pretty good too on regular hardware?