Re:How we got Stable Diffusion XL inference to under 2 seconds
by Tenoke on Friday September 01, 2023 @06:17AM
(#37348866)
It's a bit weird to talk about steps but not about the sampler (20 steps with Euler vs 20 steps in DPM+2M Karras are pretty different beasts both in terms of speed and quality).
I also see compiling but no AITemplate, which seems to be the among the hottest way to speed-up SD recently.
I also see compiling but no AITemplate, which seems to be the among the hottest way to speed-up SD recently.