--- title: Rethinking How to Train Diffusion Models | daily.dev description: The post discusses the training dynamics of diffusion models and the problems caused by weight and activation growth. It introduces a remedy for eliminating... canonical: https://daily.dev/posts/rethinking-how-to-train-diffusion-models-pksrsn462 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Rethinking How to Train Diffusion Models | daily.dev og:description: The post discusses the training dynamics of diffusion models and the problems caused by weight and activation growth. It introduces a remedy for eliminating... og:url: https://daily.dev/posts/rethinking-how-to-train-diffusion-models-pksrsn462 og:image: https://api.daily.dev/og/posts/PksRSN462.png og:image:alt: Rethinking How to Train Diffusion Models og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Rethinking How to Train Diffusion Models **[NVIDIA Developer](https://daily.dev/sources/nvidiadev)** · 11 min read · 0 upvotes · 0 comments ## Summary The post discusses the training dynamics of diffusion models and the problems caused by weight and activation growth. It introduces a remedy for eliminating weight and activation growth and controlling learning rate decay. The findings are applicable not only to diffusion models but also to other neural networks. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: --- Tags: [#diffusion-models](https://daily.dev/tags/diffusion-models) [View this post on daily.dev](https://daily.dev/posts/rethinking-how-to-train-diffusion-models-pksrsn462) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Rethinking How to Train Diffusion Models","url":"https://daily.dev/posts/rethinking-how-to-train-diffusion-models-pksrsn462","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/rethinking-how-to-train-diffusion-models-pksrsn462"},"datePublished":"2024-03-21T13:13:57.314Z","dateModified":"2024-05-09T09:06:08.895Z","description":"The post discusses the training dynamics of diffusion models and the problems caused by weight and activation growth. It introduces a remedy for eliminating...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/e54a8ff8aa718e21fec3c2458cead065?_a=AQAEufR","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/e54a8ff8aa718e21fec3c2458cead065?_a=AQAEufR","isAccessibleForFree":true,"articleSection":"NVIDIA Developer","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"NVIDIA Developer","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/86e45aab42ba48ce83103d01b1119910","url":"https://daily.dev/sources/nvidiadev"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/rethinking-how-to-train-diffusion-models-pksrsn462","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"diffusion-models","timeRequired":"PT11M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"NVIDIA Developer","item":"https://daily.dev/sources/nvidiadev"},{"@type":"ListItem","position":3,"name":"Rethinking How to Train Diffusion Models"}]} ```