正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

WebGPU is the future! 😍🔥 Transformers.js can now perform real-time background removal, powered by MODNet! ⚡️ Development for Transformers.js v3 (which adds full WebGPU support) is well underway, and we're excited to continue sharing updates and demos! Try it out yourself! 👇

Xenova

17,212 subscribers

46,513 次观看 • 2 年前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

9 条评论

kache 的头像

kache2 年前

:) keep it up man

Furkan Gözükara 的头像

Furkan Gözükara2 年前

Nice

takeyourmeds 的头像

takeyourmeds2 年前

I can't even make the webgpu API work real time w the llm so annoying I hope you guys get it right

SteveyB 的头像

SteveyB2 年前

been waiting for something like this for so long

田中義弘 | taziku CEO / AI × Creative 的头像

田中義弘 | taziku CEO / AI × Creative2 年前

Now the video is in real time. It's amazing what you can do with a browser.

Cristian Peñas ░░░░░░░░ 的头像

Cristian Peñas ░░░░░░░░2 年前

Just for my understanding, what is the difference between this new method and the old ones used by programs like Zoom? 🤔

Hieu 🚀 的头像

Hieu 🚀2 年前

Is v3 available for testing yet? Can’t wait to try it out

Xenova 的头像

Xenova2 年前

It is! 🚀 You can follow the instructions in the first comment for how to get started: Just remember that everything is still a work-in-progress, and the APIs may change before release!

Lin Wang 的头像

Lin Wang2 年前

Nice. Can you share github? Thank you

相关视频

Introducing TTS WebGPU: The first ever text-to-speech web app built with WebGPU acceleration! 🔥 High-quality and natural speech generation that runs 100% locally in your browser, powered by OuteTTS and Transformers.js.🤗 Try it out yourself! Demo + source code below 👇

Introducing TTS WebGPU: The first ever text-to-speech web app built with WebGPU acceleration! 🔥 High-quality and natural speech generation that runs 100% locally in your browser, powered by OuteTTS and Transformers.js.🤗 Try it out yourself! Demo + source code below 👇

Xenova

19,666 次观看 • 1 年前

Introducing SmolVLM 256M (& 500M): The world’s smallest multimodal model. Designed for efficiency and perfect for on-device applications! 🔥 It’s so small, it can even run 100% locally in your browser on WebGPU! 🤏 Powered by Transformers.js! ⚡️ Try it out yourself! 👇

Introducing SmolVLM 256M (& 500M): The world’s smallest multimodal model. Designed for efficiency and perfect for on-device applications! 🔥 It’s so small, it can even run 100% locally in your browser on WebGPU! 🤏 Powered by Transformers.js! ⚡️ Try it out yourself! 👇

Xenova

24,966 次观看 • 1 年前

Realtime Particle test using Transformers.js by Xenova and its upcoming WebGPU backend with the Xenova/modnet model for body segmentation. Rendered with WebGPU in Three.js. It’s so clean it makes me want to do a shadertoy visualizer in the background now 😄 #threejs

Realtime Particle test using Transformers.js by Xenova and its upcoming WebGPU backend with the Xenova/modnet model for body segmentation. Rendered with WebGPU in Three.js. It’s so clean it makes me want to do a shadertoy visualizer in the background now 😄 #threejs

Renaud

13,713 次观看 • 2 年前

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

117,665 次观看 • 2 年前

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

42,863 次观看 • 10 个月前

Introducing Moonshine Web: real-time speech recognition running 100% locally in your browser! 🚀 Faster and more accurate than Whisper 🔒 Privacy-focused (no data leaves your device) ⚡️ WebGPU accelerated (w/ WASM fallback) 🔥 Powered by ONNX Runtime Web and Transformers.js

Introducing Moonshine Web: real-time speech recognition running 100% locally in your browser! 🚀 Faster and more accurate than Whisper 🔒 Privacy-focused (no data leaves your device) ⚡️ WebGPU accelerated (w/ WASM fallback) 🔥 Powered by ONNX Runtime Web and Transformers.js

Xenova

27,878 次观看 • 1 年前

I don't think people realize how versatile WebGPU is! 🤯 In this demo, *both* the semantic search model and Earth shaders are running on WebGPU (via Transformers.js and Three.js, respectively). Pretty insane.

I don't think people realize how versatile WebGPU is! 🤯 In this demo, both the semantic search model and Earth shaders are running on WebGPU (via Transformers.js and Three.js, respectively). Pretty insane.

Xenova

18,317 次观看 • 2 个月前

RF-DETR, the state-of-the-art model series for real-time object detection, can now run 100% locally in your browser on WebGPU with 🤗 Transformers.js v4! The models are Apache-2.0 licensed, making them a perfect fit for both personal and commercial applications. Try the demo 👇

RF-DETR, the state-of-the-art model series for real-time object detection, can now run 100% locally in your browser on WebGPU with 🤗 Transformers.js v4! The models are Apache-2.0 licensed, making them a perfect fit for both personal and commercial applications. Try the demo 👇

Xenova

77,043 次观看 • 4 个月前

Transformers.js v3 is finally out - WebGPU support (up to 100x faster than WASM) - New quantization formats (dtypes) - 120 supported architectures in total - 25 new example projects and templates - Over 1200 pre-converted models - Node.js (ESM + CJS), Deno, and Bun compatibility - A new home on GitHub and NPM

Transformers.js v3 is finally out - WebGPU support (up to 100x faster than WASM) - New quantization formats (dtypes) - 120 supported architectures in total - 25 new example projects and templates - Over 1200 pre-converted models - Node.js (ESM + CJS), Deno, and Bun compatibility - A new home on GitHub and NPM

Rohan Paul

74,202 次观看 • 1 年前

Florence-2, the new vision foundation model by Microsoft, can now run 100% locally in your browser on WebGPU, thanks to Transformers.js! 🤗🤯 It supports tasks like image captioning, optical character recognition, object detection, and many more! 😍 WOW! Demo (+ source code) 👇

Florence-2, the new vision foundation model by Microsoft, can now run 100% locally in your browser on WebGPU, thanks to Transformers.js! 🤗🤯 It supports tasks like image captioning, optical character recognition, object detection, and many more! 😍 WOW! Demo (+ source code) 👇

Xenova

88,743 次观看 • 2 年前

Okay, this is actually insane... You can now run LFM2.5-1.2B-Thinking (a 1.2B parameter LLM from @LiquidAI) at over 200 tokens per second directly in your browser on WebGPU! 🤯 Zero install. Fully private. Blazingly fast. Powered by Transformers.js and ONNX Runtime Web

Okay, this is actually insane... You can now run LFM2.5-1.2B-Thinking (a 1.2B parameter LLM from @LiquidAI) at over 200 tokens per second directly in your browser on WebGPU! 🤯 Zero install. Fully private. Blazingly fast. Powered by Transformers.js and ONNX Runtime Web

Xenova

103,001 次观看 • 3 个月前

"Free background-image remover in the browser!" ⚡️ Happy to share a free little app that removes backgrounds from images directly in your browser! Privacy-friendly. Uses Transformers.js and for models RMBG-1.4 & MODNet. Inspired by Xenova

"Free background-image remover in the browser!" ⚡️ Happy to share a free little app that removes backgrounds from images directly in your browser! Privacy-friendly. Uses Transformers.js and for models RMBG-1.4 & MODNet. Inspired by Xenova

Addy Osmani

48,900 次观看 • 1 年前

After more than a year of development, we're excited to announce the release of 🤗 Transformers.js v3! ⚡ WebGPU support (up to 100x faster than WASM) 🔢 New quantization formats (dtypes) 🏛 120 supported architectures in total 📂 25 new example projects and templates 🤖 Over 1200 pre-converted models 🌐 Node.js (ESM + CJS), Deno, and Bun compatibility 🏡 A new home on GitHub and NPM Get started with `npm i @huggingface/transformers`. Learn more in the blog post below! 👇

After more than a year of development, we're excited to announce the release of 🤗 Transformers.js v3! ⚡ WebGPU support (up to 100x faster than WASM) 🔢 New quantization formats (dtypes) 🏛 120 supported architectures in total 📂 25 new example projects and templates 🤖 Over 1200 pre-converted models 🌐 Node.js (ESM + CJS), Deno, and Bun compatibility 🏡 A new home on GitHub and NPM Get started with `npm i @huggingface/transformers`. Learn more in the blog post below! 👇

Xenova

43,403 次观看 • 1 年前

WebGPU is INSANE! 🤯 Here's a 24B parameter model running locally in a web browser, at a blazing ~50 tokens/second on my M4 Max. ⚡️ It's the largest model we've ever run with Transformers.js... and we're not stopping here. Big announcement soon.

WebGPU is INSANE! 🤯 Here's a 24B parameter model running locally in a web browser, at a blazing ~50 tokens/second on my M4 Max. ⚡️ It's the largest model we've ever run with Transformers.js... and we're not stopping here. Big announcement soon.

Xenova

36,159 次观看 • 2 个月前

Introducing Kokoro.js, a new JavaScript library for running Kokoro TTS, an 82 million parameter text-to-speech model, 100% locally in the browser w/ WASM. Powered by 🤗 Transformers.js. WebGPU support coming soon! 👉 npm i kokoro-js 👈 Link to demo (+ sample code) in 🧵

Introducing Kokoro.js, a new JavaScript library for running Kokoro TTS, an 82 million parameter text-to-speech model, 100% locally in the browser w/ WASM. Powered by 🤗 Transformers.js. WebGPU support coming soon! 👉 npm i kokoro-js 👈 Link to demo (+ sample code) in 🧵

Xenova

40,340 次观看 • 1 年前

IBM just released Granite 4.0, their latest series of small language models! These models excel at agentic workflows (tool calling), document analysis, RAG, and more. 🚀 The "Micro" (3.4B) model can even run 100% locally in your browser on WebGPU, powered by 🤗 Transformers.js!

IBM just released Granite 4.0, their latest series of small language models! These models excel at agentic workflows (tool calling), document analysis, RAG, and more. 🚀 The "Micro" (3.4B) model can even run 100% locally in your browser on WebGPU, powered by 🤗 Transformers.js!

Xenova

82,893 次观看 • 8 个月前

NEW: Alibaba just released Qwen 3.5 Small — a family of powerful multimodal models available in a range of sizes (0.8B, 2B, 4B, and 9B parameters). Perfect for on-device applications! They can even run 100% locally in your browser on WebGPU, powered by Transformers.js! 🤯

NEW: Alibaba just released Qwen 3.5 Small — a family of powerful multimodal models available in a range of sizes (0.8B, 2B, 4B, and 9B parameters). Perfect for on-device applications! They can even run 100% locally in your browser on WebGPU, powered by Transformers.js! 🤯

Xenova

102,592 次观看 • 3 个月前

Is this the future of AI browser agents? 👀 WebGPU-accelerated reasoning LLMs are now supported in Transformers.js! 🤯 Here's MiniThinky-v2 (1B) running 100% locally in the browser at ~60 tps (no API calls)! I can't wait to see what you build with it! Demo + source code in 🧵👇

Is this the future of AI browser agents? 👀 WebGPU-accelerated reasoning LLMs are now supported in Transformers.js! 🤯 Here's MiniThinky-v2 (1B) running 100% locally in the browser at ~60 tps (no API calls)! I can't wait to see what you build with it! Demo + source code in 🧵👇

Xenova

81,346 次观看 • 1 年前

Apple released FastVLM so I tried vibe coding a video captioning AI app with it took 5 prompts to get a working app in anycoder and deployed it on Hugging Face 85x faster and 3.4x smaller than comparable sized VLMs the deployed app works 100% locally in your browser powered by transformers.js and WebGPU

Apple released FastVLM so I tried vibe coding a video captioning AI app with it took 5 prompts to get a working app in anycoder and deployed it on Hugging Face 85x faster and 3.4x smaller than comparable sized VLMs the deployed app works 100% locally in your browser powered by transformers.js and WebGPU

AK

42,677 次观看 • 9 个月前

My new #threejs project is live😍. Lumen Decor features WebGPU SSGI+SSR, showcasing how sunlight can influence decoration. Everything you see renders in real-time and weighs 4MB. #creativecoding #webgpu #tsl

My new #threejs project is live😍. Lumen Decor features WebGPU SSGI+SSR, showcasing how sunlight can influence decoration. Everything you see renders in real-time and weighs 4MB. #creativecoding #webgpu #tsl

Anderson Mancini

67,985 次观看 • 7 个月前