cm0002@lemmy.world to memes@lemmy.world · 30 days agoM.A.D.'s response to LLMsfed.dyne.orgimagemessage-square30fedilinkarrow-up1595arrow-down116cross-posted to: memes@lemmy.ml
arrow-up1579arrow-down1imageM.A.D.'s response to LLMsfed.dyne.orgcm0002@lemmy.world to memes@lemmy.world · 30 days agomessage-square30fedilinkcross-posted to: memes@lemmy.ml
minus-squareLemmy See Your Wrists@lemmynsfw.comlinkfedilinkarrow-up35arrow-down1·edit-230 days agoLLMs are Large Language Models and generate text, not images. (ok, LLMs can’t count either but still)
minus-squareLem Jukes@lemm.eelinkfedilinkEnglisharrow-up2·29 days agoRight but as I said in the other thread as well, what do you think is handling the text part of text-to-image creation tools?
minus-squareEch@lemmy.worldlinkfedilinkEnglisharrow-up2·edit-229 days agoImage generators are reverse llms, tbf. Steve Mould has a good explanation of it.
minus-squarelime!@feddit.nulinkfedilinkEnglisharrow-up4·29 days agowell, ish. llms have a vector space of words, image generators of features. they use a second model to associate words with features. Steve’s explanation is a great intro but for a deep dive i recommend Self-Cannibalizing AI from 37C3.
LLMs are Large Language Models and generate text, not images.
(ok, LLMs can’t count either but still)
Right but as I said in the other thread as well, what do you think is handling the text part of text-to-image creation tools?
Image generators are reverse llms, tbf. Steve Mould has a good explanation of it.
well, ish. llms have a vector space of words, image generators of features. they use a second model to associate words with features. Steve’s explanation is a great intro but for a deep dive i recommend Self-Cannibalizing AI from 37C3.