This is 30 times faster than SD (on its own, as opposed to LCM methods) right? Noting the "50" steps they referenced- whereas I've been using LCMs with 3-8 steps for months. Just trying to understand context of the paper / comparisons etc. 90ms is fast, but like 2-3x speedup (over what I've been seeing) which is still huge, but not 30x Can someone with more context explain?
MIT Unveils Gen AI Tool That Generates High Res Images 30 Times Faster
61–63 of 63 posts
Re: MIT Unveils Gen AI Tool That Generates High Res Images 30 Times Faster
#62>Our method is similar to GANs in that a critic is jointly trained with the generator to minimize a divergence between the real and fake distributions, but differs in that our training does not play an adversarial game that may cause training instability, and our critic can fully leverage the weights of a pretrained diffusion model. Very glad to see GANs (or GAN-likes) coming back! Also I don't know if the examples w…
Re: MIT Unveils Gen AI Tool That Generates High Res Images 30 Times Faster
#63Earlier quoted context omitted.
OpenAI has been at least one year ahead of everyone else in everything they have released do far. And there’s no sign they are stopping any time soon (e.g. GPT5 is expected this year).
GPT-5 will likely only see improvements in deductive reasoning like in math, I think it there are diminishing returns if all GPT-5 is a larger transformer than GPT-4