Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Meta's Segment Anything Model (SAM) can now run in your browser w/ WebGPU (+ fp16), meaning up to 8x faster image encoding (10s → 1.25s)! 🤯⚡️ Video is not sped up! Everything runs 100% locally thanks to 🤗 Transformers.js and onnxruntime-web! 🔗 Demo:

Xenova

17,017 subscribers

120,352 views • 2 years ago •via X (Twitter)

Science & Technology News & Politics

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

IBM just released Granite 4.0 1B Speech, a compact and efficient speech-language model, designed for multilingual speech recognition and bidirectional speech translation. New #1 on the OpenASR leaderboard! It can even run in your browser on WebGPU, thanks to 🤗 Transformers.js

IBM just released Granite 4.0 1B Speech, a compact and efficient speech-language model, designed for multilingual speech recognition and bidirectional speech translation. New #1 on the OpenASR leaderboard! It can even run in your browser on WebGPU, thanks to 🤗 Transformers.js

Xenova

21,506 views • 4 months ago

WOW! 🤯 Language models are becoming smaller and more capable than ever! Here's SmolLM2 running 100% locally in-browser w/ WebGPU on a 6-year-old GPU. Look at that speed! ⚡️😍 Powered by 🤗 Transformers.js and ONNX Runtime Web! How many tokens/second do you get? Let me know! 👇

WOW! 🤯 Language models are becoming smaller and more capable than ever! Here's SmolLM2 running 100% locally in-browser w/ WebGPU on a 6-year-old GPU. Look at that speed! ⚡️😍 Powered by 🤗 Transformers.js and ONNX Runtime Web! How many tokens/second do you get? Let me know! 👇

Xenova

12,557 views • 1 year ago

Opus 4.7 just wrote a custom WebGPU kernel that runs Qwen3.5 up to 13x faster using a fused LinearAttention op! 🤯 Agentic kernel optimization is the future. Now live in 🤗 Transformers.js v4.2.0! P.S. I've updated all our previous demos to use this new version. Enjoy!

Opus 4.7 just wrote a custom WebGPU kernel that runs Qwen3.5 up to 13x faster using a fused LinearAttention op! 🤯 Agentic kernel optimization is the future. Now live in 🤗 Transformers.js v4.2.0! P.S. I've updated all our previous demos to use this new version. Enjoy!

Xenova

78,401 views • 3 months ago

This is running in my web browser on my laptop. It's deterministic and running using webgpu Tonight; I have a /goal going where it is going to set up one of my 4090s as the authority server, and then test all the rollback code. Goal is 50k boxes simmed per user, up to 512 users. Massively multiplayer massively rigid body physics online games inside your web browser. Why the hell not, we've got the tokens to spare!

This is running in my web browser on my laptop. It's deterministic and running using webgpu Tonight; I have a /goal going where it is going to set up one of my 4090s as the authority server, and then test all the rollback code. Goal is 50k boxes simmed per user, up to 512 users. Massively multiplayer massively rigid body physics online games inside your web browser. Why the hell not, we've got the tokens to spare!

kache

39,117 views • 27 days ago

⚡️Introducing Open LLM Server⚡️ Looking to run models like GPT4All or LLaMa locally, but tired of python-based UIs that are impossibly slow/clunky to install? Now with a single command you can be up and running in seconds! (Windows/Mac/Linux) Here's why this is a big deal:

⚡️Introducing Open LLM Server⚡️ Looking to run models like GPT4All or LLaMa locally, but tired of python-based UIs that are impossibly slow/clunky to install? Now with a single command you can be up and running in seconds! (Windows/Mac/Linux) Here's why this is a big deal:

dcSpark

16,499 views • 3 years ago

Here’s your video for THAT fight lol, and the highlight from that OTHER fight. Literally not worth putting up a whole video on YouTube for lol. Everything is dead, I can put this to rest now lol

Here’s your video for THAT fight lol, and the highlight from that OTHER fight. Literally not worth putting up a whole video on YouTube for lol. Everything is dead, I can put this to rest now lol

Sung Drip Woo

22,324 views • 1 year ago

Discover Passage for Creators 🌌 With Passage, you can create games and social experiences without needing to code or download anything! Here's how it works: 🎮 Make Worlds Easily: Build cool worlds in your web browser. or 👥 Create your own community, whether you're a big name, a brand, or a group. Connect with your fans using cool new social features. Easy to use for everyone, thanks to these functions: 🖌️ Drag & Drop to Customize worlds. 📱 No Apps or Downloads. Everything in the browser. 🔊 3D Sound & Video 👤 Personalized Avatars 💰 Sell Stuff in Your Worlds. Make money from your creations. Watch out for Passage; their tool is set to revolutionize the world of Web3!

Cosmos Airdrops 🪂

16,537 views • 2 years ago

🤯 THIS FEELS ILLEGAL AND I LOVE IT. I found a personal AI assistant that actually runs on your computer 24/7 and gets smarter the more you use it. It is called Mercury. 100% FREE. Think of it like having a smart assistant who never forgets anything. Here is what it does: ↳ Remembers everything about you ↳ Asks before doing anything risky It will not run commands or touch your files without permission. You stay in control always. ↳ You can message it from anywhere ↳ Has 31 tools built in ↳ Protects your AI credits One command to install: npx @cosmicstack/mercury-agent 100% OpenSource. Works on Mac, Windows, and Linux.

🤯 THIS FEELS ILLEGAL AND I LOVE IT. I found a personal AI assistant that actually runs on your computer 24/7 and gets smarter the more you use it. It is called Mercury. 100% FREE. Think of it like having a smart assistant who never forgets anything. Here is what it does: ↳ Remembers everything about you ↳ Asks before doing anything risky It will not run commands or touch your files without permission. You stay in control always. ↳ You can message it from anywhere ↳ Has 31 tools built in ↳ Protects your AI credits One command to install: npx @cosmicstack/mercury-agent 100% OpenSource. Works on Mac, Windows, and Linux.

Kanika

13,601 views • 2 months ago

Eyes Up ✅ Eyes Down ❌ Let’s talk about why: 👀 The Spine: Looking down bends your neck and breaks your posture. A neutral chin is a technique win! 👏 ⚡️ The Speed Illusion: Looking down feels faster, but it actually forces your body into a slower position. Keep your eyes up to run faster with less effort. ⬆️ The Awareness: Seeing obstacles 20 meters ahead vs. 2 feet in front of you gives you way more time to react and adjust. 😮‍💨 The Airway: Tucking your chin can slightly compress your airway. Keeping your head neutral keeps everything open for maximum breathing efficiency. Your homework today: Try looking down for a few strides, then look up. Notice the instant shift in your posture, breathing, and awareness? 👇

Eyes Up ✅ Eyes Down ❌ Let’s talk about why: 👀 The Spine: Looking down bends your neck and breaks your posture. A neutral chin is a technique win! 👏 ⚡️ The Speed Illusion: Looking down feels faster, but it actually forces your body into a slower position. Keep your eyes up to run faster with less effort. ⬆️ The Awareness: Seeing obstacles 20 meters ahead vs. 2 feet in front of you gives you way more time to react and adjust. 😮‍💨 The Airway: Tucking your chin can slightly compress your airway. Keeping your head neutral keeps everything open for maximum breathing efficiency. Your homework today: Try looking down for a few strides, then look up. Notice the instant shift in your posture, breathing, and awareness? 👇

Chari Hawkins

12,607 views • 2 months ago

Very proud to share that we just release Luce KVFlash. Run your preferred model inside Lucebox at 256k context, without thinking about KVCache and OOM, up to 2.9x faster decoding at long context. Taking inspiration from OS paging and using our speculative prefill method (Luce PFlash), we managed to make KV vram usage almost constant. Offloading what is not needed dynamically. Opensource must win now more than ever.

Very proud to share that we just release Luce KVFlash. Run your preferred model inside Lucebox at 256k context, without thinking about KVCache and OOM, up to 2.9x faster decoding at long context. Taking inspiration from OS paging and using our speculative prefill method (Luce PFlash), we managed to make KV vram usage almost constant. Offloading what is not needed dynamically. Opensource must win now more than ever.

mrciffa

25,228 views • 1 month ago

Seedance 2.5 is now available on CapCut. Create and edit AI videos in one seamless workflow. What stands out: • More controllable video generation and editing • Timestamp-based storyline control • Support for up to 50 reference images • Generate videos up to 90 seconds • Viewport render and green screen workflows • Enhanced multilingual performance From your first prompt to the final edit, everything stays inside CapCut. Try it here: 🌐 Web: 📱 App: #CapCut #Seedance25 #CapCutai #CapCutDidThat

Seedance 2.5 is now available on CapCut. Create and edit AI videos in one seamless workflow. What stands out: • More controllable video generation and editing • Timestamp-based storyline control • Support for up to 50 reference images • Generate videos up to 90 seconds • Viewport render and green screen workflows • Enhanced multilingual performance From your first prompt to the final edit, everything stays inside CapCut. Try it here: 🌐 Web: 📱 App: #CapCut #Seedance25 #CapCutai #CapCutDidThat

Akash

14,197 views • 9 days ago

(1/n) 🚀 With FastVideo, you can now generate a 5-second video in 5 seconds on a single H200 GPU! Introducing FastWan series, a family of fast video generation models trained via a new recipe we term as “sparse distillation”, to speed up video denoising time by 70X! 🖥️ Live demo: (Thanks to @gmicloud for the support!) 🔗 Blog: 🔓 We fully open-source our models, code, and data with Apache-2.0 licenses

(1/n) 🚀 With FastVideo, you can now generate a 5-second video in 5 seconds on a single H200 GPU! Introducing FastWan series, a family of fast video generation models trained via a new recipe we term as “sparse distillation”, to speed up video denoising time by 70X! 🖥️ Live demo: (Thanks to @gmicloud for the support!) 🔗 Blog: 🔓 We fully open-source our models, code, and data with Apache-2.0 licenses

Hao AI Lab

78,660 views • 1 year ago

This tool is literally Higgsfield AI but FREE for good. It's called Wan2GP. A full AI video studio built specifically for people without expensive hardware. Runs on as little as 6GB of VRAM, even old RTX 10-series cards and 8GB laptops. Everything stays on your machine, no uploads, no caps, no watermarks. What you get in one app: • Text-to-video and image-to-video generation • The best open models built in: Wan 2.2, LTX-2, Hunyuan Video, Flux • A full browser interface with a queue system • LoRA support to customize any model • Mask editor and prompt enhancer included A 5-second clip generates in minutes on a mid-range gaming rig. No subscription, ever. 100% Free. Open Source.

This tool is literally Higgsfield AI but FREE for good. It's called Wan2GP. A full AI video studio built specifically for people without expensive hardware. Runs on as little as 6GB of VRAM, even old RTX 10-series cards and 8GB laptops. Everything stays on your machine, no uploads, no caps, no watermarks. What you get in one app: • Text-to-video and image-to-video generation • The best open models built in: Wan 2.2, LTX-2, Hunyuan Video, Flux • A full browser interface with a queue system • LoRA support to customize any model • Mask editor and prompt enhancer included A 5-second clip generates in minutes on a mid-range gaming rig. No subscription, ever. 100% Free. Open Source.

Simplifying AI

174,193 views • 11 days ago

How to use China's best AI video model (Seedance 2.0) completely free and without watermarks. Most people think you need expensive subscriptions or get stuck with watermarked outputs (mandatory in China). Not if you use this loophole. The Setup • VPN to Hong Kong/China (only to start download). • Download the "Doubao" app from doubao[dot]com. • Install (Android: allow from browser / iOS: switch appstore region to HK). • Register with a non-US phone number, if you're from US and need a SMS service DM me, I'll send you one. The "Glitch" Workflow The Seedance 2.0 feature in app often fails. Do this instead: • Toggle Image Model (Seedream 4.5). • Type your prompt. • Add this specific text at the end: "generate video, not the image". • Result: 10s video, bypassing the busy server errors. How to Remove the Watermark If you save directly, it stamps it. Here is the fix: • Tap Share → Copy Link. • Open that link in your mobile browser. • Long press video → Download. Congratulations, you just got the clean video without watermarks. Total Cost: $0 Daily Limit: 5 free videos per account This method is only one so far. Bookmark if you need this.

How to use China's best AI video model (Seedance 2.0) completely free and without watermarks. Most people think you need expensive subscriptions or get stuck with watermarked outputs (mandatory in China). Not if you use this loophole. The Setup • VPN to Hong Kong/China (only to start download). • Download the "Doubao" app from doubao[dot]com. • Install (Android: allow from browser / iOS: switch appstore region to HK). • Register with a non-US phone number, if you're from US and need a SMS service DM me, I'll send you one. The "Glitch" Workflow The Seedance 2.0 feature in app often fails. Do this instead: • Toggle Image Model (Seedream 4.5). • Type your prompt. • Add this specific text at the end: "generate video, not the image". • Result: 10s video, bypassing the busy server errors. How to Remove the Watermark If you save directly, it stamps it. Here is the fix: • Tap Share → Copy Link. • Open that link in your mobile browser. • Long press video → Download. Congratulations, you just got the clean video without watermarks. Total Cost: $0 Daily Limit: 5 free videos per account This method is only one so far. Bookmark if you need this.

Alchemiz

16,853 views • 5 months ago

A guy in Vancouver built an entire operating system inside a Chrome tab. By himself. Over six years. His personal website is the OS. You open and a Windows-style desktop loads. File explorer. Start menu. Taskbar. You can drag in a zip and extract it. You can play DOOM. You can play Quake III Arena. You can boot Linux from an ISO. You can run Stable Diffusion locally for image generation. You can open a Python terminal. You can edit code in Monaco, the same engine that powers VS Code. All of it runs in your browser tab. Nothing installs. His name is Dustin Brett. Self-taught engineer. Father. Husband. 4,473 commits. All his. He had to swap the Windows icon for the π symbol because of legal pressure. The repo has 12,883 stars. MIT license. His hosting bill is one dollar a month. A single Cloudflare CDN does the rest. This is what the open web was built for. (Link in the comments)

A guy in Vancouver built an entire operating system inside a Chrome tab. By himself. Over six years. His personal website is the OS. You open and a Windows-style desktop loads. File explorer. Start menu. Taskbar. You can drag in a zip and extract it. You can play DOOM. You can play Quake III Arena. You can boot Linux from an ISO. You can run Stable Diffusion locally for image generation. You can open a Python terminal. You can edit code in Monaco, the same engine that powers VS Code. All of it runs in your browser tab. Nothing installs. His name is Dustin Brett. Self-taught engineer. Father. Husband. 4,473 commits. All his. He had to swap the Windows icon for the π symbol because of legal pressure. The repo has 12,883 stars. MIT license. His hosting bill is one dollar a month. A single Cloudflare CDN does the rest. This is what the open web was built for. (Link in the comments)

Nav Toor

72,629 views • 1 month ago

Meta just launched its 1st image model after Mark Zuckerberg’s AI shake-up. Muse Image is Meta Superintelligence Labs' first image generator after Muse Spark. They said the model will power new editing features in Meta’s Instagram photo app and be added to its marketer tools for creating platform ads. Meta had relied on Midjourney and Black Forest Labs for generation inside Meta AI. Muse Image brings that layer in-house, so Meta controls quality, cost, and product timing. Consumers get free access through Meta AI, WhatsApp chats, and Instagram Stories. Power users need Meta One or another monthly plan when free limits run out. Users can start from prompts, add photos, annotate edits, or sketch changes directly. Meta says it can erase photobombers, create QR codes, and keep visual text readable. Advertisers get variants through Advantage+ creative, with edits, style swaps, and brand-matched versions. Meta says internal tests trail GPT Image 2 but beat Nano Banana 2 on editing. This is another move in Meta's effort in trying to convert AI infrastructure spending into revenue beyond social ads.

Rohan Paul

20,377 views • 1 month ago

LTX-2.3 is now live on OpenArt. 🎬 The most capable open video model just got a major upgrade and you can use it right now. What's new in 2.3: → Sharper fine detail: Hair, textures, text, edges. All of it. → Tighter prompt adherence: Complex multi-subject prompts? Handle it. → Stronger image-to-video: less freezing, less Ken Burns drift, more actual motion. → Cleaner audio: fewer artifacts, tighter sync across text-to-video and audio workflows. → Native portrait: up to 1080×1920, trained on vertical data.

LTX-2.3 is now live on OpenArt. 🎬 The most capable open video model just got a major upgrade and you can use it right now. What's new in 2.3: → Sharper fine detail: Hair, textures, text, edges. All of it. → Tighter prompt adherence: Complex multi-subject prompts? Handle it. → Stronger image-to-video: less freezing, less Ken Burns drift, more actual motion. → Cleaner audio: fewer artifacts, tighter sync across text-to-video and audio workflows. → Native portrait: up to 1080×1920, trained on vertical data.

OpenArt

2,151,015 views • 3 months ago

MY CLIPPING AGENT GOT 166,000+ VIEWS!! 🤯 I have a 24/7 marketing agent INSIDE MY PHONE thanks to Vugola!! All I do is send YT links and he does the clipping, captions, and scheduling. Organic marketing has never been easier until now. 99% of the world doesn’t even know this tool exists. 🤫 You can set this up in your Telegram, Discord, or WhatsApp. p.s beta is now live for you to try!!

MY CLIPPING AGENT GOT 166,000+ VIEWS!! 🤯 I have a 24/7 marketing agent INSIDE MY PHONE thanks to Vugola!! All I do is send YT links and he does the clipping, captions, and scheduling. Organic marketing has never been easier until now. 99% of the world doesn’t even know this tool exists. 🤫 You can set this up in your Telegram, Discord, or WhatsApp. p.s beta is now live for you to try!!

Vadim

28,996 views • 5 months ago

This is how you unlock the next billion software developers. The new Replit ⠕ Agent 3 (they just launched) is the most advanced vibe-coding agent in the world. 1. Smarter than any other vibe-coding model (10x more autonomous than the previous version). 2. It thinks harder and lasts longer than any other model (up to 200 minutes running fully autonomously). 3. The agent can now use an actual browser to test and fix its own code. 4. 3x faster and 10x more cost-effective than any other "Computer Use" for testing. 5. It can build other agents and automations to take care of repetitive tasks. Seeing the agent test the application autonomously is science fiction!

This is how you unlock the next billion software developers. The new Replit ⠕ Agent 3 (they just launched) is the most advanced vibe-coding agent in the world. 1. Smarter than any other vibe-coding model (10x more autonomous than the previous version). 2. It thinks harder and lasts longer than any other model (up to 200 minutes running fully autonomously). 3. The agent can now use an actual browser to test and fix its own code. 4. 3x faster and 10x more cost-effective than any other "Computer Use" for testing. 5. It can build other agents and automations to take care of repetitive tasks. Seeing the agent test the application autonomously is science fiction!

Santiago

167,056 views • 11 months ago