Y
Hacker News
new
|
ask
|
show
|
jobs
by
WithinReason
611 days ago
I meant sequential generation, I didn't mean using an RNN.
Diffusion doesn't work on pixels directly either, it works on a latent representation.
1 comments
kleiba
611 days ago
All NNs work on latent representations.
link
barrkel
611 days ago
The contrast here is real: there are pixel space diffusion models and latent space diffusion models. Pixel space diffusion is slower because there's more redundant information.
link