--- title: Client side AI model inference for real-time video processi… description: A team built a real-time, browser-based neural style transfer solution that runs entirely client-side on CPU. Starting from a feed-forward network based on the... canonical: https://daily.dev/posts/client-side-ai-model-inference-for-real-time-video-processi--kpvmkqkra twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Client side AI model inference for real-time video processi… | daily.dev og:description: A team built a real-time, browser-based neural style transfer solution that runs entirely client-side on CPU. Starting from a feed-forward network based on the... og:url: https://daily.dev/posts/client-side-ai-model-inference-for-real-time-video-processi--kpvmkqkra og:image: https://api.daily.dev/og/posts/KpVmKQKRA.png og:image:alt: Client side AI model inference for real-time video processi… 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. # Client side AI model inference for real-time video processi… **[Software Mansion](https://daily.dev/sources/swmansion)** · 6 min read · 0 upvotes · 0 comments ## Summary A team built a real-time, browser-based neural style transfer solution that runs entirely client-side on CPU. Starting from a feed-forward network based on the 'Perceptual Losses' paper, they applied aggressive optimizations including channel reduction, knowledge distillation, skip connection removal, and the netAdapt compression algorithm to achieve 20–30ms inference on CPU — with one model being ~400x smaller than the original. Deployment used ONNX format with onnxruntime-web, requiring careful CORS configuration for SharedArrayBuffer multithreading. Instance normalization layer weights are exposed as sliders for real-time style blending without re-rendering. The post concludes that on-device ML inference is viable and increasingly attractive with emerging technologies like WebGPU. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [WebGPU Browser AI: Client-Side Inference in JavaScript](https://daily.dev/posts/webgpu-browser-ai-client-side-inference-in-javascript-qmvpskeqv) · SitePoint · 0 upvotes · 0 comments - [How Google Is Shifting AI From the Cloud to Your Browser](https://daily.dev/posts/how-google-is-shifting-ai-from-the-cloud-to-your-browser-gdtsilce3) · The New Stack · 1 upvotes · 0 comments - [LiteRT.js, Google's high performance Web AI Inference](https://daily.dev/posts/litert-js-google-s-high-performance-web-ai-inference-trneihldh) · Google Developers · 3 upvotes · 0 comments - [WebGPU Browser AI: Run LLMs Client-Side, No Backend](https://daily.dev/posts/webgpu-browser-ai-run-llms-client-side-no-backend-1evlxlfvf) · SitePoint · 0 upvotes · 0 comments - [QCon London 2026: Running AI at the Edge - Running Real Workloads Directly in the Browser](https://daily.dev/posts/qcon-london-2026-running-ai-at-the-edge---running-real-workloads-directly-in-the-browser-fmvixbzwo) · InfoQ · 1 upvotes · 0 comments --- Tags: [#machine-learning](https://daily.dev/tags/machine-learning), [#webassembly](https://daily.dev/tags/webassembly) [View this post on daily.dev](https://daily.dev/posts/client-side-ai-model-inference-for-real-time-video-processi--kpvmkqkra) ```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":"Client side AI model inference for real-time video processi…","url":"https://daily.dev/posts/client-side-ai-model-inference-for-real-time-video-processi--kpvmkqkra","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/client-side-ai-model-inference-for-real-time-video-processi--kpvmkqkra"},"datePublished":"2026-08-02T07:16:02.008Z","dateModified":"2026-08-02T07:42:12.736Z","description":"A team built a real-time, browser-based neural style transfer solution that runs entirely client-side on CPU. Starting from a feed-forward network based on the...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/9ddd3b34193d2be2f2657ba53e24a998?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/9ddd3b34193d2be2f2657ba53e24a998?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Software Mansion","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":"Software Mansion","logo":"https://media.daily.dev/image/upload/s--sOx0vaVZ--/f_auto,q_auto/v1785654908/logos/swmansion?_a=BAMAMicg0","url":"https://daily.dev/sources/swmansion"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/client-side-ai-model-inference-for-real-time-video-processi--kpvmkqkra","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"machine-learning,webassembly","timeRequired":"PT6M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Software Mansion","item":"https://daily.dev/sources/swmansion"},{"@type":"ListItem","position":3,"name":"Client side AI model inference for real-time video processi…"}]} ```