News for hackers. Stuff that matters.

A comment on Diffusion Models Are Real-Time Game Engines. Parent comment

Re:Diffusion Models Are Real-Time Game Engines by injidup on Wednesday August 28, 2024 @02:04AM (#41376426)
Why games? I will train it on 1 years worth of me attending Microsoft teams meetings. Then I will go surfing.
[ Parent | on HN ]
Re:Diffusion Models Are Real-Time Game Engines by akie on Wednesday August 28, 2024 @05:20AM (#41377618)
Ready to pay for this
[ Parent | on HN ]
Re:Diffusion Models Are Real-Time Game Engines by ccozan on Wednesday August 28, 2024 @06:54AM (#41378144)
most underrated comment here!
[ Parent | on HN ]
Re:Diffusion Models Are Real-Time Game Engines by kqr on Wednesday August 28, 2024 @07:00AM (#41378184)
Even if you spend 40 hours a week in video conferences, you'll have to work for over four years to get one years' worth of footage. Of course, by then the models will be even better and so you might actually have a chance of going surfing.

I guess I should start hoarding video of myself now.

[ Parent | on HN ]
Re:Diffusion Models Are Real-Time Game Engines by kragen on Wednesday August 28, 2024 @08:08AM (#41378573)
the neural net doesn't need a year of video to train to simulate your face; it can do that from a single photo. the year of video is to learn how to play the game, and in most cases lots of people are playing the same game, so you can dump all their video in the same training set
[ Parent | on HN ]