@hayek@feddit.de to Technology@lemmy.worldEnglish • 2 years 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.commessage-square10fedilinkarrow-up198arrow-down16file-textcross-posted to: technews@radiation.partyhackernews@derp.foo
arrow-up192arrow-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.com@hayek@feddit.de to Technology@lemmy.worldEnglish • 2 years agomessage-square10fedilinkfile-textcross-posted to: technews@radiation.partyhackernews@derp.foo
minus-squareJackGreenEarthlinkfedilinkEnglish10•2 years agoRelease it, and let us see. Don’t just claim stuff.
Release it, and let us see. Don’t just claim stuff.