taming-transformers icon indicating copy to clipboard operation
taming-transformers copied to clipboard

Published 20 hours ago • verified publisher icon CompVis

Parameters to use less memory

Open kstroevsky opened this issue 4 years ago • 2 comments
trafficstars

Hello! Now I'm trying to generate some pictures by vqgan+clip on my laptop with 2GB VRAM. Obviously I get some errors of out of memory. That's about my question.

What's the parameters of models can give me an opportunity to use less memory to the detriment of, for example, time or performance? Are there in configs is .yaml files?

kstroevsky avatar Jul 10 '21 12:07 kstroevsky

you would probably need 10 - 20 GB of ram. I don't think there's any way to reduce this. I use vast.ai to train models. RTX 3090 seems to be the gpu to train with.

adeptflax avatar Jul 13 '21 04:07 adeptflax

i'am new around here with my rtx 3080 and about 2 days on this tech, but i still think that using a 7gb for model.decode is kinda vicious each time :) maybe we can look together into this issue?

danilaplee avatar Feb 14 '22 04:02 danilaplee