Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

MIT Unveils Gen AI Tool That Generates High Res Images 30 Times Faster

hothardware.com

Post reply on HN
Print view View original

31–40 of 63 posts

Re: MIT Unveils Gen AI Tool That Generates High Res Images 30 Times Faster

#31

Post by jzbontar »

albert_e wrote: post #15

Is the text prompt input the only common thing between SD and MIT models when comparing outputs? If so I am surprised at how SIMILAR the outputs of both models look in the general layout / framing / composition of the image. How can for example both fox astronaut images have near identical backdrop of earth and earth alone on the same side of image at same apparent size. Virtually the same shade of deep blue for deep…

I assume those images were generated using the same text prompt as well as the same initial random noise.

Re: MIT Unveils Gen AI Tool That Generates High Res Images 30 Times Faster

#37

Post by amelius »

fngjdflmdflg wrote: post #7

>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…

Can GANs prevent the ">10 fingers" problem?

Re: MIT Unveils Gen AI Tool That Generates High Res Images 30 Times Faster

#38

Post by fzliu »

amelius wrote: post #37
fngjdflmdflg wrote: post #7

>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…

Can GANs prevent the ">10 fingers" problem?

The >10 fingers problem should be solved via higher quality data or conditioning rather than a better model architecture.

Re: MIT Unveils Gen AI Tool That Generates High Res Images 30 Times Faster

#39

Post by onion2k »

fzliu wrote: post #38
amelius wrote: post #37

Earlier quoted context omitted.

Can GANs prevent the ">10 fingers" problem?

The >10 fingers problem should be solved via higher quality data or conditioning rather than a better model architecture.

Are you suggesting AI generates images of people with more than 10 fingers because there are too many pictures of people with more than 10 fingers in the input data? That seems unlikely..

Re: MIT Unveils Gen AI Tool That Generates High Res Images 30 Times Faster

#40

Post by Drakim »

onion2k wrote: post #39
fzliu wrote: post #38

Earlier quoted context omitted.

The >10 fingers problem should be solved via higher quality data or conditioning rather than a better model architecture.

Are you suggesting AI generates images of people with more than 10 fingers because there are too many pictures of people with more than 10 fingers in the input data? That seems unlikely..

In some pictures not all 5 fingers on a hand are visible, so maybe it appears that humans have a variable amount of fingers?
Post reply on HN