Tiny-diffusion: A minimal implementation of probabilistic diffusion models

Tiny-diffusion: A minimal implementation of probabilistic diffusion models(github.com)

96 points by BraverHeart 1 year ago | 5 comments

aestuans 1 year 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 1 year ago |

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

endymion-light 1 year 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 1 year ago | | |

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

barbarr 1 year ago |

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