@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-square9arrow-up199file-textcross-posted to: hackernews@derp.footechnews@radiation.party
arrow-up199external-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-square9file-textcross-posted to: hackernews@derp.footechnews@radiation.party
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.