[pilooch]

Exactly, for real time applications VTO, simulators,...), i.e. 60+FPS, diffusion can't be used efficiently. The gap is still there afaik. One lead has been to distill DPM into GANs, not sure this works for GANs that are small enough for real time.

[godelski]

I mean it is really hard to push diffusion models down in size so that just makes the speed part hard. I'm not sure diffusion can ever truly win in the speed race, at least without additional context like breadth of generation. But isn't that the thing? The best model is only the best in a given context?

I think the weirdest thing in ML has always been acting like there's an objectively better model and no context is needed.