Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

Real-time video captioning in your browser with @LiquidAI's LFM2-VL model on WebGPU. Sending every frame to a server was never going to be the answer. Imagine the bandwidth, latency and cost. Local inference. No server costs. Infinitely scalable. This is the way.

Xenova

20,428 subscribers

48,798 просмотров • 6 месяцев назад •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Introducing Voxtral WebGPU: Real-time speech transcription entirely in your browser. This demo runs Voxtral-Mini-4B, a powerful streaming ASR model from Mistral AI, locally on WebGPU. The model supports 13 languages and is capable of <500 ms latency. Fully private. Zero cost.

Introducing Voxtral WebGPU: Real-time speech transcription entirely in your browser. This demo runs Voxtral-Mini-4B, a powerful streaming ASR model from Mistral AI, locally on WebGPU. The model supports 13 languages and is capable of <500 ms latency. Fully private. Zero cost.

Xenova

94,623 просмотров • 6 месяцев назад

Okay this is insane... WebGPU-accelerated semantic video tracking, powered by DINOv3 and Transformers.js! 🤯 This will revolutionize AI-powered video editors... which can now run 100% locally in your browser, no server inference required (costs $0)! 😍 Who's building this?

Okay this is insane... WebGPU-accelerated semantic video tracking, powered by DINOv3 and Transformers.js! 🤯 This will revolutionize AI-powered video editors... which can now run 100% locally in your browser, no server inference required (costs $0)! 😍 Who's building this?

Xenova

42,882 просмотров • 1 год назад

I'm obsessed with pushing local small models to their limits. Qwen3.5:0.8b doing real-time video captioning on a Mac Studio M2 Ultra, streaming descriptions as the video plays. Under 1s per frame — 269 frames captured & described from a 3m49s video. Pause anywhere and read the captions, it describes every frame surprisingly well. This model is barely 1GB. Local AI is moving absurdly fast.

I'm obsessed with pushing local small models to their limits. Qwen3.5:0.8b doing real-time video captioning on a Mac Studio M2 Ultra, streaming descriptions as the video plays. Under 1s per frame — 269 frames captured & described from a 3m49s video. Pause anywhere and read the captions, it describes every frame surprisingly well. This model is barely 1GB. Local AI is moving absurdly fast.

stevibe

106,441 просмотров • 6 месяцев назад

Introducing Phi-3 WebGPU, a private and powerful AI chatbot that runs locally in your browser, powered by 🤗 Transformers.js and onnxruntime-web! 🔒 On-device inference: no data sent to a server ⚡️ WebGPU-accelerated (> 20 t/s) 📥 Model downloaded once and cached Try it out! 👇

Introducing Phi-3 WebGPU, a private and powerful AI chatbot that runs locally in your browser, powered by 🤗 Transformers.js and onnxruntime-web! 🔒 On-device inference: no data sent to a server ⚡️ WebGPU-accelerated (> 20 t/s) 📥 Model downloaded once and cached Try it out! 👇

Xenova

117,724 просмотров • 2 лет назад

Woah... This is the fastest Transformers.js has ever been! 🤯 Run a 1.7B LLM 100% locally in your browser at over 130 tokens per second! 🚀 No server required. ⚡️ WebGPU-accelerated in-browser inference 📦 Optimized ONNX exports w/ GQA 💬 Multi-round conversations w/ KV caching

Woah... This is the fastest Transformers.js has ever been! 🤯 Run a 1.7B LLM 100% locally in your browser at over 130 tokens per second! 🚀 No server required. ⚡️ WebGPU-accelerated in-browser inference 📦 Optimized ONNX exports w/ GQA 💬 Multi-round conversations w/ KV caching

Xenova

54,099 просмотров • 1 год назад

This SDR web server is pretty sweet. The server is portable Rust, it supports several SDRs like the Pluto, RTL-SDR, RFSPACE radios and the browser does the demodulation. Running well on real hardware, with more features on the way.

This SDR web server is pretty sweet. The server is portable Rust, it supports several SDRs like the Pluto, RTL-SDR, RFSPACE radios and the browser does the demodulation. Running well on real hardware, with more features on the way.

RFSPΔCΞ

10,783 просмотров • 2 месяцев назад

$What if psql had an \ai command? This is PGlite (WASM Postgres) and Llama3 (via WebLLM & WebGPU) running completely in the browser - no cloud, no server🤯 Local AI is coming sooner than you think!$

What if psql had an \ai command? This is PGlite (WASM Postgres) and Llama3 (via WebLLM & WebGPU) running completely in the browser - no cloud, no server🤯 Local AI is coming sooner than you think!

Sam Willis

21,688 просмотров • 2 лет назад

Our research team just released Flex-Forcing: a video generation method that lets a single model switch between generation methods at inference time. Right now there are two main approaches to video generation. Bidirectional diffusion models attend to every frame at once, holding structure well at the cost of speed. Autoregressive models generate frame by frame, so they stream fast and scale to long clips, but accumulate error and drift over time. Flex-Forcing trains a single model to do both, letting you choose from the range at inference based on your compute budget.

Our research team just released Flex-Forcing: a video generation method that lets a single model switch between generation methods at inference time. Right now there are two main approaches to video generation. Bidirectional diffusion models attend to every frame at once, holding structure well at the cost of speed. Autoregressive models generate frame by frame, so they stream fast and scale to long clips, but accumulate error and drift over time. Flex-Forcing trains a single model to do both, letting you choose from the range at inference based on your compute budget.

NVIDIA AI

31,412 просмотров • 2 месяцев назад

Internet Identity is getting an MCP server. We sat down with Arshavir Ter-Gabrielyan to understand what it is and why it matters. He starts with the problem: an AI agent runs in a cloud sandbox. No access to your device. No safe way to hold your keys. The MCP server is the answer. Keys stay in a trusted execution environment, and the agent asks permission to act in each app. Full conversation below.

Internet Identity is getting an MCP server. We sat down with Arshavir Ter-Gabrielyan to understand what it is and why it matters. He starts with the problem: an AI agent runs in a cloud sandbox. No access to your device. No safe way to hold your keys. The MCP server is the answer. Keys stay in a trusted execution environment, and the agent asks permission to act in each app. Full conversation below.

DFINITY Foundation

32,824 просмотров • 2 месяцев назад

Before Fable 5 was shut down, it pushed Gemma 4 to 255 tok/s on WebGPU. Some didn't believe it was real. Today we're releasing the demo and kernels it wrote for you to see yourself. Run it locally in your browser. Agentic kernel optimization is the future of on-device inference

Before Fable 5 was shut down, it pushed Gemma 4 to 255 tok/s on WebGPU. Some didn't believe it was real. Today we're releasing the demo and kernels it wrote for you to see yourself. Run it locally in your browser. Agentic kernel optimization is the future of on-device inference

Xenova

485,535 просмотров • 3 месяцев назад

Introducing Virtuals Console. The easiest way to create your own AI agent in seconds. No code. No Mac. No server. No setup. Just open a browser and get started.

Introducing Virtuals Console. The easiest way to create your own AI agent in seconds. No code. No Mac. No server. No setup. Just open a browser and get started.

Virtuals Protocol

221,069 просмотров • 5 месяцев назад

made an interactive video model trained on tap-conditioned data.. tap the screen and it generates the next frames in realtime (small enough to run in the browser with webgpu, even on iphone)

made an interactive video model trained on tap-conditioned data.. tap the screen and it generates the next frames in realtime (small enough to run in the browser with webgpu, even on iphone)

sahir

25,027 просмотров • 5 месяцев назад

We made an interactive client-server viewer for LagerNVS with Jonathon Luiten! You can now interactively explore scenes from just a photo capture - no optimization, no 3D Gaussians, just load your images, run the model on a cloud GPU and stream the renders to your local browser. Check out the video below for some spaces I recently captured in Oxford, London and beyond!

We made an interactive client-server viewer for LagerNVS with Jonathon Luiten! You can now interactively explore scenes from just a photo capture - no optimization, no 3D Gaussians, just load your images, run the model on a cloud GPU and stream the renders to your local browser. Check out the video below for some spaces I recently captured in Oxford, London and beyond!

Stan Szymanowicz

17,188 просмотров • 4 месяцев назад

⚡Technical Showcase: Peer-to-peer GPU sharing, entirely in the browser. AI Grid lets you run LLMs locally with WebGPU and either donate your spare compute to the network or borrow from someone else's machine. No installs, no cloud. Decentralized inference with nothing but a URL. 🔗 #WebGPU #WebLLM #WebAI #DistributedCompute #ArtificialInteligence

⚡Technical Showcase: Peer-to-peer GPU sharing, entirely in the browser. AI Grid lets you run LLMs locally with WebGPU and either donate your spare compute to the network or borrow from someone else's machine. No installs, no cloud. Decentralized inference with nothing but a URL. 🔗 #WebGPU #WebLLM #WebAI #DistributedCompute #ArtificialInteligence

WebGL / WebGPU

17,200 просмотров • 7 месяцев назад

In the next two or three years, every human could have a hundred... maybe a thousand agents working for them onchain. Arpan Nanavati breaks it down perfectly in this clip... the whole thing is a cost curve. Right now, it costs about $10 a day in inference to run an agent... hedge fund territory. But inference costs have already dropped 100x in three years, and every step down changes who can afford to play: At $1 a day, every protocol is running agents At cents a day, your wallet has agents built in, managing your idle capital At microcents, you get agent swarms Jevons paradox... every time the cost of something collapses, usage explodes. Intelligence is scaling, and theres no reason the number of agents executing onchain cant scale near infinitely. Madness.

In the next two or three years, every human could have a hundred... maybe a thousand agents working for them onchain. Arpan Nanavati breaks it down perfectly in this clip... the whole thing is a cost curve. Right now, it costs about $10 a day in inference to run an agent... hedge fund territory. But inference costs have already dropped 100x in three years, and every step down changes who can afford to play: At $1 a day, every protocol is running agents At cents a day, your wallet has agents built in, managing your idle capital At microcents, you get agent swarms Jevons paradox... every time the cost of something collapses, usage explodes. Intelligence is scaling, and theres no reason the number of agents executing onchain cant scale near infinitely. Madness.

Raoul Pal

565,927 просмотров • 21 дней назад

🙌 There will be no server layering in Ashes of Creation! All the players you see and encounter will be there in real time playing along with you. Do you prefer this? Let us know your experiences with server layering in the comments!

🙌 There will be no server layering in Ashes of Creation! All the players you see and encounter will be there in real time playing along with you. Do you prefer this? Let us know your experiences with server layering in the comments!

Ashes of Creation

17,639 просмотров • 2 лет назад

Smooth by Smooth is a real-time AI browser agent - and the fastest and most reliable one yet. It can autonomously perform any task on the web using mouse and keyboard. Infinitely scalable, production-ready, and secure, it's now available as a serverless API with instant browser spin-up and persistent sessions.

Smooth by Smooth is a real-time AI browser agent - and the fastest and most reliable one yet. It can autonomously perform any task on the web using mouse and keyboard. Infinitely scalable, production-ready, and secure, it's now available as a serverless API with instant browser spin-up and persistent sessions.

Y Combinator

33,958 просмотров • 11 месяцев назад

Took it further with Omma AI, (Spline ) now it works on video, and everything working in a Web Browser. Drop a video, Depth Anything v2 calculates the depth map frame by frame, and Three.js renders a fully lit 3D mesh in real time. Depth estimation on video in the browser +Automatic baking pass + Dynamic lighting reacting to the geometry #vibecoding #threejs #webgl

Took it further with Omma AI, (Spline ) now it works on video, and everything working in a Web Browser. Drop a video, Depth Anything v2 calculates the depth map frame by frame, and Three.js renders a fully lit 3D mesh in real time. Depth estimation on video in the browser +Automatic baking pass + Dynamic lighting reacting to the geometry #vibecoding #threejs #webgl

Joseph Azar

148,148 просмотров • 4 месяцев назад

The headshot animations seem to be faster. Tests need to be replicated more for confirmation. This is with loopback=0. With latency on a server results may vary more. (Not a fact :/ it's a theory)

CS2 Kitchen

109,804 просмотров • 7 месяцев назад

sneak-peek:🎈@partykit/react, the one framework to rule them all - Real-time React Server Components! - Keep business/rendering logic on the server, send UI over the wire in real-time - Zero API setup - one party per user, or per shared session, or even the whole world (scales to thousands of connections per instance) - Wire up your own reactive sources - Super fast "local" state, with ultra low latency syncing, powered by PartyKit - optional SSR / prerendering What would you build with this?

sneak-peek:🎈@partykit/react, the one framework to rule them all - Real-time React Server Components! - Keep business/rendering logic on the server, send UI over the wire in real-time - Zero API setup - one party per user, or per shared session, or even the whole world (scales to thousands of connections per instance) - Wire up your own reactive sources - Super fast "local" state, with ultra low latency syncing, powered by PartyKit - optional SSR / prerendering What would you build with this?

sunil pai

142,949 просмотров • 2 лет назад