Loading video...

Video Failed to Load

Go Home

Introducing MirageLSD: The First Live-Stream Diffusion (LSD) AI Model Input any video stream, from a camera or video chat to a computer screen or game, and transform it into any world you desire, in real-time (<40ms latency). Here’s how it works (w/ demo you can use!):

DecartAI's profile picture

Decart

20,913 subscribers

1,007,791 views • 10 months ago •via X (Twitter)

Science & TechnologyGamingArts
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

🎉 Today at Decart we're announcing Mirage. The first generative video model that runs in real-time, to infinity. Mirage is a Live Stream Diffusion (LSD), a breakthrough that transforms any video into anything you can imagine, as it plays. 🎮 Try it:
0:39

🎉 Today at Decart we're announcing Mirage. The first generative video model that runs in real-time, to infinity. Mirage is a Live Stream Diffusion (LSD), a breakthrough that transforms any video into anything you can imagine, as it plays. 🎮 Try it:

Kfir Aberman

37,114 views • 10 months ago

Introducing Lemon Slice Live: the first real-time audio-video AI model Anyone can video chat with any character by just uploading a single photo. Every pixel on the screen is rendered at 25fps in real-time by a transformer model. Here’s how we built it + a live demo! 👇
0:23

Introducing Lemon Slice Live: the first real-time audio-video AI model Anyone can video chat with any character by just uploading a single photo. Every pixel on the screen is rendered at 25fps in real-time by a transformer model. Here’s how we built it + a live demo! 👇

LemonSlice

170,779 views • 1 year ago

Introducing Oasis: the first playable AI-generated game. We partnered with Decart to build a real-time, interactive world model that runs >10x faster on Sohu. We're open-sourcing the model architecture, weights, and research. Here's how it works (and a demo you can play!):
0:24

Introducing Oasis: the first playable AI-generated game. We partnered with Decart to build a real-time, interactive world model that runs >10x faster on Sohu. We're open-sourcing the model architecture, weights, and research. Here's how it works (and a demo you can play!):

Etched

24,645,225 views • 1 year ago

Stability AI just dropped Stable Virtual Camera on Hugging Face a generalist diffusion model designed to address the exciting challenge of Novel View Synthesis (NVS). With just one or a few images, it allows you to create a smooth trajectory video from any viewpoint you desire.
1:00

Stability AI just dropped Stable Virtual Camera on Hugging Face a generalist diffusion model designed to address the exciting challenge of Novel View Synthesis (NVS). With just one or a few images, it allows you to create a smooth trajectory video from any viewpoint you desire.

AK

133,583 views • 1 year ago

Introducing AI video you can watch and interact with, in real-time! Powering this is a new world model that imagines and streams video frames every 40ms(!). No game engine in sight. We call it interactive video, and it's free for anyone to try right now (GPUs permitting)!
0:32

Introducing AI video you can watch and interact with, in real-time! Powering this is a new world model that imagines and streams video frames every 40ms(!). No game engine in sight. We call it interactive video, and it's free for anyone to try right now (GPUs permitting)!

Odyssey

704,384 views • 1 year ago

Introducing Oasis 2.0: Our most advanced AI model Transform game worlds & styles in real time. 1080p, 30fps Here’s how to play it live (and also a Minecraft Mod)! 🧵
0:28

Introducing Oasis 2.0: Our most advanced AI model Transform game worlds & styles in real time. 1080p, 30fps Here’s how to play it live (and also a Minecraft Mod)! 🧵

Decart

2,332,981 views • 9 months ago

Introducing a beautifully designed AI chat component! 🎉 ◆ Ready to use, drop into any existing project ◆ Stream AI responses in real time ◆ Built-in RAG functionality Beautiful out of the box, fully customizable. 30-second demo 👇🏻
0:27

Introducing a beautifully designed AI chat component! 🎉 ◆ Ready to use, drop into any existing project ◆ Stream AI responses in real time ◆ Built-in RAG functionality Beautiful out of the box, fully customizable. 30-second demo 👇🏻

Upstash

45,838 views • 1 year ago

This is so cool: LSD v2 is a next-generation real-time video-to-video model that restyles your live video as it’s playing. It delivers higher consistency, better quality, stronger context understanding, and reliable identity preservation. You can use it to transform live events, reskin games, or stream yourself in entirely new styles instantly. I had the privilege of speaking with their CEO and one of their researchers in a video call, so they told me about their projects. Really exciting!
0:36

This is so cool: LSD v2 is a next-generation real-time video-to-video model that restyles your live video as it’s playing. It delivers higher consistency, better quality, stronger context understanding, and reliable identity preservation. You can use it to transform live events, reskin games, or stream yourself in entirely new styles instantly. I had the privilege of speaking with their CEO and one of their researchers in a video call, so they told me about their projects. Really exciting!

Chubby♨️

28,245 views • 6 months ago

Introducing Lyria 3, our new music generation model in Gemini that lets you turn any idea, photo, or video into a high-fidelity track with custom lyrics. From funny jingles to lo-fi beats, you can create custom 30-second soundtracks for any moment. See how it works. 🧵
1:03

Introducing Lyria 3, our new music generation model in Gemini that lets you turn any idea, photo, or video into a high-fidelity track with custom lyrics. From funny jingles to lo-fi beats, you can create custom 30-second soundtracks for any moment. See how it works. 🧵

Google Gemini

4,647,070 views • 3 months ago

Making a 30s video used to take me 2 hours… Now it takes me 3 minutes. OpenArt Story just changed the game. You can use it to turn any idea into a stunning, AI-generated video, with motion, music, and a full narrative arc. Here’s how it works + a great opportunity to win some $$
0:48

Making a 30s video used to take me 2 hours… Now it takes me 3 minutes. OpenArt Story just changed the game. You can use it to turn any idea into a stunning, AI-generated video, with motion, music, and a full narrative arc. Here’s how it works + a great opportunity to win some $$

Amira Zairi

135,733 views • 9 months ago

Swaps are now live on our website, powered by Enso | ⌘ 🛠️. You can swap any asset directly in the dapp or deploy into any active campaign from the swaps page. Here’s how it works 👇
0:41

Swaps are now live on our website, powered by Enso | ⌘ 🛠️. You can swap any asset directly in the dapp or deploy into any active campaign from the swaps page. Here’s how it works 👇

Turtle

19,282 views • 1 year ago

Realtime edit is an insane new model. It generates images with near-zero latency based on your reference input(s) and prompt. You can draw, upload images, or even stream video 🤯 I got early access from KREA AI. Two of my favorite use cases so far 👇
0:29

Realtime edit is an insane new model. It generates images with near-zero latency based on your reference input(s) and prompt. You can draw, upload images, or even stream video 🤯 I got early access from KREA AI. Two of my favorite use cases so far 👇

Justine Moore

91,506 views • 4 months ago

🎥 Curious how Akool Live Camera works? Eugene from our Akool team breaks it down in this quick demo — showing how you can use our real-time AI video tool in your daily workflow, virtual meetings, or content creation. From live translations to facial reenactments and expressive avatars, it’s never been easier to communicate across borders, cultures, and languages. 🌍 Whether you're a creator, educator, or business professional — this is the future of live video. 🚀 Watch the demo now and see Akool Live Camera in action! #AkoolLiveCamera #GenerativeAI #AIAvatars #FutureOfWork #AIinAction #RealTimeVideo #DigitalAvatars #Akool
2:44

🎥 Curious how Akool Live Camera works? Eugene from our Akool team breaks it down in this quick demo — showing how you can use our real-time AI video tool in your daily workflow, virtual meetings, or content creation. From live translations to facial reenactments and expressive avatars, it’s never been easier to communicate across borders, cultures, and languages. 🌍 Whether you're a creator, educator, or business professional — this is the future of live video. 🚀 Watch the demo now and see Akool Live Camera in action! #AkoolLiveCamera #GenerativeAI #AIAvatars #FutureOfWork #AIinAction #RealTimeVideo #DigitalAvatars #Akool

Akool Inc

169,190 views • 1 year ago

AI can now make you a great parent. Introducing Ollie: the world’s first AI family assistant that manages your family life better than any human. Here’s how it works:
1:50

AI can now make you a great parent. Introducing Ollie: the world’s first AI family assistant that manages your family life better than any human. Here’s how it works:

Bill Lennon

2,014,719 views • 8 days ago

Today we announced RTFM (Real-Time Frame Model) — a world model that generates frames in real time from any camera viewpoint. Unlike standard video models, RTFM understands 3D geometry. You can literally move the camera through the generated world. 🎥👇
2:21

Today we announced RTFM (Real-Time Frame Model) — a world model that generates frames in real time from any camera viewpoint. Unlike standard video models, RTFM understands 3D geometry. You can literally move the camera through the generated world. 🎥👇

Keunhong Park

15,653 views • 7 months ago

Our third announcement is GWM Worlds. A world model for real-time environment simulation. You give the model a static scene, and it generates an immersive, infinite, explorable space as you move through it, with geometry, lighting and physics. All in real-time. You can travel to any place, real or imagined. You can become any agent, a person walking through a city, a drone flying over a snowy mountain or a robot navigating a warehouse.
1:15

Our third announcement is GWM Worlds. A world model for real-time environment simulation. You give the model a static scene, and it generates an immersive, infinite, explorable space as you move through it, with geometry, lighting and physics. All in real-time. You can travel to any place, real or imagined. You can become any agent, a person walking through a city, a drone flying over a snowy mountain or a robot navigating a warehouse.

Runway

80,075 views • 6 months ago

Wow, diffusion models (used in AI image generation) are also game engines - a type of world simulation. By predicting the next frame of the classic shooter DOOM, you get a playable game at 20 fps without any underlying real game engine. This video is from the diffusion model.
2:30

Wow, diffusion models (used in AI image generation) are also game engines - a type of world simulation. By predicting the next frame of the classic shooter DOOM, you get a playable game at 20 fps without any underlying real game engine. This video is from the diffusion model.

Ethan Mollick

1,768,598 views • 1 year ago

Been doing some serious work on a creator SaaS for the past few weeks. is finally live. You can input any YouTube video link or paste any newsletter, article, or document. And it will provide you with viral X and LinkedIn posts.
0:54

Been doing some serious work on a creator SaaS for the past few weeks. is finally live. You can input any YouTube video link or paste any newsletter, article, or document. And it will provide you with viral X and LinkedIn posts.

Muzzammil

142,262 views • 1 year ago

Google offers a AI-powered personal assistant that you can use for free. You can talk to it in real time, share your screen with it, and ask it to help you with any given task (sound on 👇). Surprisingly, not many people are using it. Here's how to use it:
0:23

Google offers a AI-powered personal assistant that you can use for free. You can talk to it in real time, share your screen with it, and ask it to help you with any given task (sound on 👇). Surprisingly, not many people are using it. Here's how to use it:

Mushtaq Bilal, PhD

44,529 views • 1 year ago