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.

Nearly real-time diffusion model, running locally and offline from my browser and with decent output quality. Pretty astonishing to use; but with such a tight feedback loop, the textual interface starts to feel really inadequate.

Matt DesLauriers

60,884 subscribers

122,502 views • 2 years ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

10 Comments

anotherjesse2 years ago

I'm super excited to see what generative artists / javascript hackers build integrating with things like this.. I built a quick prototype using @p5xjs You draw on the canvas - and it re-runs @SimianLuo's LCM after mouseup... I have a little more info here: It is so fun to be able to interactively play play with genai via drawing & code in near realtime

Diego2 years ago

nice! in-browser inference? what stack?

Matt DesLauriers2 years ago

Thanks! I should clarify, it’s running in Python and passing images to the browser with websockets. Only a matter of time before we see this tech running natively in a browser though. 😀

Kristian Muñiz2 years ago

Wait, this is running in the browser or do you mean running in your machine and served to your browser?

Radamés Ajna2 years ago

Very cool ! Are you running LCM?

Matt DesLauriers2 years ago

Yep!

Henry Daubrez 🌸💀2 years ago

A stone throw to verbal expression to replace the text-box and likely a control-net scribble to refine composition as you go. You push of this on a haptic device or tablet screen and you have a pretty instinctive way to create

Kristian Muñiz2 years ago

HOW?

Jason Mayes2 years ago

Wow. This is epic!!

Valent2 years ago

very nice! is the rendering progressive or keystrokes firing multiple generations?

Related Videos

Deepseek running locally and privately for autocompletion in VSCode! 🙌 In less than a minute, I'll show you how to download Deepseek-coder and set it as the autocompletion model in VSCode. You’ll need to use ollama to download the model and CodeGPT to select it as the autocompletion model. Enjoy the best models running locally with :)

Deepseek running locally and privately for autocompletion in VSCode! 🙌 In less than a minute, I'll show you how to download Deepseek-coder and set it as the autocompletion model in VSCode. You’ll need to use ollama to download the model and CodeGPT to select it as the autocompletion model. Enjoy the best models running locally with :)

Daniel San

991,258 views • 1 year ago

Introducing DeepSeek R1:1.5b Running Locally in Cursor! In less than 4 minutes, I set up the DeepSeek R1:1.5b model, download it, and run it locally to seamlessly work with code in Cursor The video is shown in real-time, with the model impressively running on an Intel Core i5 😱 using Ollama and the CodeGPT extension 👇

Introducing DeepSeek R1:1.5b Running Locally in Cursor! In less than 4 minutes, I set up the DeepSeek R1:1.5b model, download it, and run it locally to seamlessly work with code in Cursor The video is shown in real-time, with the model impressively running on an Intel Core i5 😱 using Ollama and the CodeGPT extension 👇

Daniel San

584,021 views • 1 year ago

branching interface for writing a tighter creative feedback loop guided by a language model to weave through the possibility space of text

branching interface for writing a tighter creative feedback loop guided by a language model to weave through the possibility space of text

Azlen

53,043 views • 1 year ago

You can now chat locally with AI and your PDFs completely offline. Blueshell runs in your browser and doesn't communicate with any server. No installation and open source. Here's how to access it:

You can now chat locally with AI and your PDFs completely offline. Blueshell runs in your browser and doesn't communicate with any server. No installation and open source. Here's how to access it:

Paul Couvert

42,331 views • 1 year ago

say hello to my little friend 🤖 3D model control (move, rotate, scale, animate) using hand gestures and voice commands, running in real-time in the browser! created with Three.js, Rosebud AI, mediapipe computer vision, and web speech API credit to Quaternius for the robot model 🔗 demo below

say hello to my little friend 🤖 3D model control (move, rotate, scale, animate) using hand gestures and voice commands, running in real-time in the browser! created with Three.js, Rosebud AI, mediapipe computer vision, and web speech API credit to Quaternius for the robot model 🔗 demo below

AA

30,775 views • 1 year ago

Free UE5 AI Motion Capture Plugin — also compatible with Unity, Blender, and VMC. Connects to a 1080P webcam and runs locally with a 1-billion-parameter model, requiring 8GB of GPU memory for real-time processing. The free version supports single-camera real-time capture and unlimited video uploads. Includes facial, body, and finger motion capture. Completely free to use.

Free UE5 AI Motion Capture Plugin — also compatible with Unity, Blender, and VMC. Connects to a 1080P webcam and runs locally with a 1-billion-parameter model, requiring 8GB of GPU memory for real-time processing. The free version supports single-camera real-time capture and unlimited video uploads. Includes facial, body, and finger motion capture. Completely free to use.

Cyanpuppets

25,637 views • 1 year ago

Free Blender AI motion capture plugin — also compatible with UE and Unity. Connects to a 1080P webcam and runs locally with a 1-billion-parameter model, requiring 8GB of GPU memory for real-time processing. Supports single-camera real-time capture and video uploads with no limit on the number of uploads. Includes full-body, facial, and finger motion capture. Completely free to use.

Free Blender AI motion capture plugin — also compatible with UE and Unity. Connects to a 1080P webcam and runs locally with a 1-billion-parameter model, requiring 8GB of GPU memory for real-time processing. Supports single-camera real-time capture and video uploads with no limit on the number of uploads. Includes full-body, facial, and finger motion capture. Completely free to use.

CYANPUPPETS

109,041 views • 1 year ago

We’ve upgraded Stable Video Diffusion 4D to Stable Video 4D 2.0 (SV4D 2.0), improving the quality of 4D outputs generated from a single object-centric video. While 3D provides a static view of an object’s shape and size; 4D extends this by including time, showing how the object moves. This multi-view video diffusion model generates a 4D output in three steps: 1️⃣ Starts with an input video of a moving person or object 2️⃣ Generates novel views of the subject from unseen angles 3️⃣ Constructs a single dynamic 4D video output with spatial and temporal consistency You can learn more here: (1/4)

We’ve upgraded Stable Video Diffusion 4D to Stable Video 4D 2.0 (SV4D 2.0), improving the quality of 4D outputs generated from a single object-centric video. While 3D provides a static view of an object’s shape and size; 4D extends this by including time, showing how the object moves. This multi-view video diffusion model generates a 4D output in three steps: 1️⃣ Starts with an input video of a moving person or object 2️⃣ Generates novel views of the subject from unseen angles 3️⃣ Constructs a single dynamic 4D video output with spatial and temporal consistency You can learn more here: (1/4)

Stability AI

35,974 views • 1 year ago

Free Blender AI motion capture plugin — also compatible with UE and Unity. Connects to a 1080P webcam and runs locally with a 1-billion-parameter model, requiring 8GB of GPU memory for real-time processing. Supports single-camera real-time capture and video uploads with no limit on the number of uploads. Includes full-body, facial, and finger motion capture. Completely free to use.

Free Blender AI motion capture plugin — also compatible with UE and Unity. Connects to a 1080P webcam and runs locally with a 1-billion-parameter model, requiring 8GB of GPU memory for real-time processing. Supports single-camera real-time capture and video uploads with no limit on the number of uploads. Includes full-body, facial, and finger motion capture. Completely free to use.

CYANPUPPETS

57,643 views • 1 year ago

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 views • 3 months ago

Real-time social robotics, from the cloud to your local device. Watch Ian from our DevX team use Gemini Live for a seamless voice chat with Reachy Mini. Then, stick around until the end to see the robot running locally on Gemma 4!

Real-time social robotics, from the cloud to your local device. Watch Ian from our DevX team use Gemini Live for a seamless voice chat with Reachy Mini. Then, stick around until the end to see the robot running locally on Gemma 4!

Google Gemma

111,935 views • 1 month ago

I made a site that uses WebGPU to run Qwen3 .6b with thinking locally, directly in your browser, no installation or servers necessary and runs offline Available forever for free and open source:

I made a site that uses WebGPU to run Qwen3 .6b with thinking locally, directly in your browser, no installation or servers necessary and runs offline Available forever for free and open source:

Surya

167,509 views • 7 months ago

OmniParser, the new screen parsing tool from Microsoft (and #1 trending model on Hugging Face), can now run 100% locally in your browser with Transformers.js! 🤯 Who's going to be the first to turn this into a browser extension? 👀 Endless possibilities! Demo & code below! 👇

OmniParser, the new screen parsing tool from Microsoft (and #1 trending model on Hugging Face), can now run 100% locally in your browser with Transformers.js! 🤯 Who's going to be the first to turn this into a browser extension? 👀 Endless possibilities! Demo & code below! 👇

Xenova

64,553 views • 1 year ago

Real-time webcam demo with Hugging Face SmolVLM and ggml llama.cpp server. All running locally on a Macbook M3

Real-time webcam demo with Hugging Face SmolVLM and ggml llama.cpp server. All running locally on a Macbook M3

Xuan-Son Nguyen

973,705 views • 1 year ago

An AVATAR program developed with UE5 that supports connecting to AI motion capture for real-time, high-quality UE animation output. It features a highly flexible character customization system and rich clothing and accessory assets. You can upload images to generate 3D models and quickly obtain high-quality 3D model assets.

CYANPUPPETS

11,542 views • 5 months ago

Blender AI Motion Plugin — a 1-billion-parameter motion model trained on NVIDIA CUDA, running locally in real time with 8GB of VRAM. It converts webcam or video footage into real-time XYZ skeletal point data and rotation values, transmitting them to Blender, Unity, and UE for retargeting.

Blender AI Motion Plugin — a 1-billion-parameter motion model trained on NVIDIA CUDA, running locally in real time with 8GB of VRAM. It converts webcam or video footage into real-time XYZ skeletal point data and rotation values, transmitting them to Blender, Unity, and UE for retargeting.

CYANPUPPETS

124,727 views • 6 months ago

Blender AI Motion Plugin — a 1-billion-parameter motion model trained on NVIDIA CUDA, running locally in real time with 8GB of VRAM. It converts webcam or video footage into real-time XYZ skeletal point data and rotation values, transmitting them to Blender, Unity, and UE for retargeting.

Blender AI Motion Plugin — a 1-billion-parameter motion model trained on NVIDIA CUDA, running locally in real time with 8GB of VRAM. It converts webcam or video footage into real-time XYZ skeletal point data and rotation values, transmitting them to Blender, Unity, and UE for retargeting.

CYANPUPPETS

18,317 views • 7 months ago

Blender AI Motion Plugin — a 1-billion-parameter motion model trained on NVIDIA CUDA, running locally in real time with 8GB of VRAM. It converts webcam or video footage into real-time XYZ skeletal point data and rotation values, transmitting them to Blender, Unity, and UE for retargeting.

Blender AI Motion Plugin — a 1-billion-parameter motion model trained on NVIDIA CUDA, running locally in real time with 8GB of VRAM. It converts webcam or video footage into real-time XYZ skeletal point data and rotation values, transmitting them to Blender, Unity, and UE for retargeting.

CYANPUPPETS

32,379 views • 8 months ago

Edit Images with NOTHING but prompts, locally, with 1 Click. Differential Diffusion lets you edit images with nothing but prompts. And I made a Dedicated Gradio Web UI and a 1 click launcher to make it as easy as drag&drop. Runs LOCALLY on Windows, Mac, Linux.

Edit Images with NOTHING but prompts, locally, with 1 Click. Differential Diffusion lets you edit images with nothing but prompts. And I made a Dedicated Gradio Web UI and a 1 click launcher to make it as easy as drag&drop. Runs LOCALLY on Windows, Mac, Linux.

cocktail peanut

35,525 views • 2 years ago

Today, we launched browser use inside Codex to further close the build & verify loop for local development! Now, you can ask Codex to build your front end, and test it like a user would by clicking through the app. Codex sees everything a user sees through vision & checks the network/console logs to help debug & fix any issues that it finds. This change brings us closer to fully autonomous coding agents that delivers high quality and tested changes. Watch Codex test my app in the browser, catch & fix a real bug, and doing that loop again with a brand new feature.

James Sun

226,260 views • 2 months ago