Tiny-diffusion: A minimal implementation of probabilistic diffusion models github.com 96 points by BraverHeart 6 months ago
aestuans 6 months ago This is very cool. I implemented a slightly more complicated version of this with class guidance a while ago: https://github.com/aestuans/mnist-diffusion
aswanson 6 months ago This is where I see edge ai going. Minimal implementations running on embedded systems everywhere. endymion-light 6 months ago Full agree - this is where AI is finding it's main useful niche. Massive models are fun to use but specialization within embedded systems is the clincher. sitkack 6 months ago Having AI running in every edge location poses an existential threat. They will provide the peripheral sensors for a larger intelligence.
endymion-light 6 months ago Full agree - this is where AI is finding it's main useful niche. Massive models are fun to use but specialization within embedded systems is the clincher. sitkack 6 months ago Having AI running in every edge location poses an existential threat. They will provide the peripheral sensors for a larger intelligence.
sitkack 6 months ago Having AI running in every edge location poses an existential threat. They will provide the peripheral sensors for a larger intelligence.
barbarr 6 months ago Very cool showing the outputs of hyperparameter search. Hopefully this gets someone out of a tuning tarpit!
This is very cool. I implemented a slightly more complicated version of this with class guidance a while ago: https://github.com/aestuans/mnist-diffusion
This is where I see edge ai going. Minimal implementations running on embedded systems everywhere.
Full agree - this is where AI is finding it's main useful niche. Massive models are fun to use but specialization within embedded systems is the clincher.
Having AI running in every edge location poses an existential threat. They will provide the peripheral sensors for a larger intelligence.
Very cool showing the outputs of hyperparameter search. Hopefully this gets someone out of a tuning tarpit!
[dead]