News for hackers. Stuff that matters.
Re:Real-time image editing using latent consistency models by billconan on Saturday November 11, 2023 @12:05AM (#38227781)
if you are talking about latent diffusion, No, the "particle" is in a hyper-dimensional space, like for example a 10k-dimensional space. We are not supposed to interpret the meaning of that vector.

and when that particle has moved to the right location, there is a decoder that converts it into an image. The decoder network knows how to interpret it.

Re:Real-time image editing using latent consistency models by dvrp on Saturday November 11, 2023 @02:14AM (#38228219)
Exactly.

I actually wrote a micro essay on Twitter the other day about the meaning of the classic encoder decoder network. It’s beautiful.

But yeah!

-

For reference: https://x.com/asciidiego/status/1722544108252836119

Re:Real-time image editing using latent consistency models by stavros on Saturday November 11, 2023 @04:20AM (#38228727)
Does this mean that you need this vector state in order to generate the next step? Ie I can't take an image (the pixels) and the prompt and run a few more steps on it?