Tiny-diffusion: A minimal implementation of probabilistic diffusion models

Y	Hacker News new \| ask \| show \| jobs

	Tiny-diffusion: A minimal implementation of probabilistic diffusion models (github.com)
	96 points by BraverHeart 366 days ago

3 comments

aestuans 366 days 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

link

aswanson 366 days ago

This is where I see edge ai going. Minimal implementations running on embedded systems everywhere.

link

endymion-light 365 days 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.

link

sitkack 363 days ago

Having AI running in every edge location poses an existential threat. They will provide the peripheral sensors for a larger intelligence.

link

barbarr 366 days ago

Very cool showing the outputs of hyperparameter search. Hopefully this gets someone out of a tuning tarpit!

link