Re:Imagen, a text-to-image diffusion model
by Nition on Tuesday May 24, 2022 @04:40PM
(#31497317)
Nice. Latent-diffusion has come out very traditional but the VQGAN/CLIP ones are fairly original.
[ Parent
| on HN ]
Re:Imagen, a text-to-image diffusion model
by zimpenfish on Tuesday May 24, 2022 @05:04PM
(#31497525)
From my experiments, the LD one doesn't seem to have been trained on as big or as tagged data set - there's a whole bunch of "in the style of X" that the VQGAN knows* about but the LD doesn't. That might have something to do with it.