hayek@feddit.de to Technology@lemmy.worldEnglish · 11 months agoNvidia released a paper about a 100KB text-to-image model that only trained for 4 minutes but claims to be better than bigger modelsresearch.nvidia.comexternal-linkmessage-square6fedilinkarrow-up196arrow-down16file-textcross-posted to: hackernews@derp.foo
arrow-up190arrow-down1external-linkNvidia released a paper about a 100KB text-to-image model that only trained for 4 minutes but claims to be better than bigger modelsresearch.nvidia.comhayek@feddit.de to Technology@lemmy.worldEnglish · 11 months agomessage-square6fedilinkfile-textcross-posted to: hackernews@derp.foo
minus-squareJackGreenEarth@lemm.eelinkfedilinkEnglisharrow-up9·11 months agoRelease it, and let us see. Don’t just claim stuff.
Release it, and let us see. Don’t just claim stuff.