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.

Diffusion Models

315 pointsby reasonableklout12 months ago

7 comments

sashank_150912 months ago
Good post, I always thought diffusion originated from score matching, today I realized diffusion came before score matching theory, so when OpenAI trained on 250 million images, they didn’t even have great theory explaining why they were modeling the underlying distribution. Gutsy move
评论 #40485578 未加载
ilaksh12 months ago
What's the best Apache or MIT-licensed python library for Diffusion Transformers?
评论 #40479008 未加载
评论 #40479798 未加载
评论 #40480030 未加载
davidguetta12 months ago
How is doing classifier-free guidance where you<p>&quot;Train a single diffusion model on every training sample x0x0 twice: once paired with its class label yy, and once paired with a null class label.&quot;<p>not doing exactly the same, and having the same problem that was deemed bad in the first paragraph of the same section:<p>&quot;However, the label can sometimes lead to samples that are not realistic or lack diversity if the model has not seen enough samples from p(x∣y)p(x∣y) for a particular yy. So we often want to tune how much the model “follows” the label during generation.&quot;<p>Awesome post btw
评论 #40509413 未加载
Tao330012 months ago
&gt; I spent 2022 learning to draw and was blindsided by the rise of AI art models like Stable Diffusion. Suddenly, the computer was a better artist than I could ever hope to be.<p>I hope the author stuck with it anyway. The more AI encroaches on creative work, the more I want to tear it all down.
评论 #40485731 未加载
kmacdough12 months ago
Thanks for sharing. This has given me much more insight into how and why diffusion models work. Randomness is oddly powerful. Time to try and code one up in some suitably unsuitable language.<p>Not much to TL;DR for the comment lurkers. This post <i>is</i> the TL;DR of stable diffusion.
davidguetta12 months ago
The train loop is wrong no ? neither x0s and eps are used in the expression of xts so it loons like your training to predict random noise
评论 #40484766 未加载
评论 #40484464 未加载
sidcool12 months ago
This is a great post
评论 #40486269 未加载