hayek@feddit.de to Technology@lemmy.worldEnglish · 1 year 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-square7fedilinkarrow-up199file-textcross-posted to: technews@radiation.partyhackernews@derp.foo
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.comhayek@feddit.de to Technology@lemmy.worldEnglish · 1 year agomessage-square7fedilinkfile-textcross-posted to: technews@radiation.partyhackernews@derp.foo
minus-squarezalack@kbin.sociallinkfedilinkarrow-up11·edit-21 year agoNVIDIA’s marketing overhypes, but their technical papers tend to be very solid. Obviously it always pays to remain skeptical but they have a good track record in this case.
NVIDIA’s marketing overhypes, but their technical papers tend to be very solid. Obviously it always pays to remain skeptical but they have a good track record in this case.