TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Introduction to Diffusion Models for Machine Learning

98 pointsby SleekEagleabout 3 years ago

3 comments

natlyabout 3 years ago
This is mostly a copy of the much better articles:<p><a href="https:&#x2F;&#x2F;yang-song.github.io&#x2F;blog&#x2F;2021&#x2F;score&#x2F;" rel="nofollow">https:&#x2F;&#x2F;yang-song.github.io&#x2F;blog&#x2F;2021&#x2F;score&#x2F;</a><p>and<p><a href="https:&#x2F;&#x2F;lilianweng.github.io&#x2F;posts&#x2F;2021-07-11-diffusion-models&#x2F;" rel="nofollow">https:&#x2F;&#x2F;lilianweng.github.io&#x2F;posts&#x2F;2021-07-11-diffusion-mode...</a>
评论 #31359575 未加载
t_mannabout 3 years ago
Interesting. So do I get this right that if you use such a model, you essentially don&#x27;t have much control over the output other than that it&#x27;s similar to your training data, because your input is just white noise? Or is there a way to bundle this with another model that would allow you to generate images based on inputs like &#x27;dog with party hat&#x27;?
评论 #31361142 未加载
dr_dshivabout 3 years ago
I followed with interest until this sentence: “ Where β 1 , . . . , β T is a variance schedule (either learned or fixed) which, if well-behaved, ensures that x T is nearly an isotropic Gaussian for sufficiently large T”
评论 #31357598 未加载
评论 #31357143 未加载
评论 #31358322 未加载