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.

Running a foundational video model in REAL-TIME on cloud, where each frame is processed in under 40 ms, requires true research + engineering superpowers. I just published a blog post breaking down how we made the impossible possible with our amazing R&D team at Decart . Link in the... show more

Kfir Aberman

1,882 subscribers

61,740 views • 7 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

A breakthrough in real-time video generation. As a research preview developed with NVIDIA and shared at NVIDIAGTC this week, we trained a new real-time video model running on Vera Rubin. HD videos generate instantly, with time-to-first-frame under 100ms. Unlocking an entirely new creative paradigm and bolstering the foundations of our General World Model, GWM-1. Real-time generation opens a fundamentally different design space for video models and world simulation. We're investing in co-designing our models alongside advances in hardware to keep pushing this frontier.

A breakthrough in real-time video generation. As a research preview developed with NVIDIA and shared at NVIDIAGTC this week, we trained a new real-time video model running on Vera Rubin. HD videos generate instantly, with time-to-first-frame under 100ms. Unlocking an entirely new creative paradigm and bolstering the foundations of our General World Model, GWM-1. Real-time generation opens a fundamentally different design space for video models and world simulation. We're investing in co-designing our models alongside advances in hardware to keep pushing this frontier.

Runway

1,162,090 views • 3 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! 👇

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

170,988 views • 1 year ago

🎥Meet Lucy Edit LIVE! The first REAL-TIME video editing model. It feels surreal to play with and is already changing how I think about AI video. And YOU CAN TRY it now in our platform @Decart →

🎥Meet Lucy Edit LIVE! The first REAL-TIME video editing model. It feels surreal to play with and is already changing how I think about AI video. And YOU CAN TRY it now in our platform @Decart →

Kfir Aberman

15,055 views • 8 months ago

Runway has unveiled a massive breakthrough in AI video generation at NVIDIA's GTC event, showcasing a new model capable of generating high-definition video in genuine real-time. The new model boasts a "time-to-first-frame" of under 100 milliseconds. This means HD video begins generating and playing almost the instant a command is given. This research preview was co-developed with NVIDIA and runs on their newly announced Vera Rubin architecture. This real-time capability is a foundational step for Runway's General World Model (GWM-1). It pushes the technology beyond simple video generation and into the realm of live, interactive environments.

Runway has unveiled a massive breakthrough in AI video generation at NVIDIA's GTC event, showcasing a new model capable of generating high-definition video in genuine real-time. The new model boasts a "time-to-first-frame" of under 100 milliseconds. This means HD video begins generating and playing almost the instant a command is given. This research preview was co-developed with NVIDIA and runs on their newly announced Vera Rubin architecture. This real-time capability is a foundational step for Runway's General World Model (GWM-1). It pushes the technology beyond simple video generation and into the realm of live, interactive environments.

Wes Roth

82,506 views • 3 months 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!):

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

24,671,181 views • 1 year ago

Always wondered where we actually use these formulas in real life? A mechanical engineer, sajjan_purushh on IG, is answering exactly that by breaking down cos ø (power factor) in workshops, showing how it quietly works behind the machines we see every day. By breaking it down into everyday examples, he shows that engineering is not just theory in books. It is already shaping how our world runs, quietly and constantly. Credits : sajjan_purushh on IG #Engineering #Physics #STEM #EngineeringLife #RealWorldLearning [Power Factor Explained, Cos Phi In Real Life, Mechanical Engineering Concepts, Practical Engineering Examples, How Machines Work]

Always wondered where we actually use these formulas in real life? A mechanical engineer, sajjan_purushh on IG, is answering exactly that by breaking down cos ø (power factor) in workshops, showing how it quietly works behind the machines we see every day. By breaking it down into everyday examples, he shows that engineering is not just theory in books. It is already shaping how our world runs, quietly and constantly. Credits : sajjan_purushh on IG #Engineering #Physics #STEM #EngineeringLife #RealWorldLearning [Power Factor Explained, Cos Phi In Real Life, Mechanical Engineering Concepts, Practical Engineering Examples, How Machines Work]

The Better India

25,301 views • 3 months ago

Our pathway to retaking the House majority is clear. We must net 3 seats, but Democrats are competing in 40+ districts! Each week, I will introduce you to our amazing candidates running in these battleground districts. Read my first post, and subscribe:

Our pathway to retaking the House majority is clear. We must net 3 seats, but Democrats are competing in 40+ districts! Each week, I will introduce you to our amazing candidates running in these battleground districts. Read my first post, and subscribe:

Lauren Underwood

11,245 views • 4 months ago

CONTROVERSY: Three years ago after I was banned on Twitter, we made a music video with the lyrics of the Prince hook changed to “Oligarchy.” The video features professional dancers, choreography done by Struther White and I. Right Down to each Frame in post, the edit was tight.

CONTROVERSY: Three years ago after I was banned on Twitter, we made a music video with the lyrics of the Prince hook changed to “Oligarchy.” The video features professional dancers, choreography done by Struther White and I. Right Down to each Frame in post, the edit was tight.

James O'Keefe

1,033,293 views • 2 years ago

To show off how fast fal's real-time LivePortrait advanced mode is, we made this demo. It is a little too fun. Link in next post 👇

To show off how fast fal's real-time LivePortrait advanced mode is, we made this demo. It is a little too fun. Link in next post 👇

Jonathan Fischoff

53,844 views • 1 year ago

The Reality portal is here, and you can test it yourself by downloading Decart XR from SideQuest 👇 It works in 3 steps: 1- Decart #XR streams the #MetaQuest camera feed to its AI models over WebRTC 2- MirageLSD the world transformation model by Decart, transforms the video in real time based on the prompt, 3- The processed feed is sent back into Unity for in-headset display. There is some latency, and every few seconds the generation kind of resets as if a new seed is generated, but this is still something that blew my mind.

The Reality portal is here, and you can test it yourself by downloading Decart XR from SideQuest 👇 It works in 3 steps: 1- Decart #XR streams the #MetaQuest camera feed to its AI models over WebRTC 2- MirageLSD the world transformation model by Decart, transforms the video in real time based on the prompt, 3- The processed feed is sent back into Unity for in-headset display. There is some latency, and every few seconds the generation kind of resets as if a new seed is generated, but this is still something that blew my mind.

Gabriele Romagnoli

10,993 views • 9 months ago

We just built the best collision prediction model on the planet. BADAS 2.0: 99.4% AP. Built on V-JEPA2, Yann LeCun's physical AI architecture. A true world model that understands reality, not just the road. Explainable. Generalizes beyond driving. Runs from cloud to edge. Our 22M model beats NVIDIA's 2B Cosmos. We published the benchmarks. We're inviting comparison. Safer roads, safer cars. That's the point. Run your own videos on BADAS 2.0, link in the first reply.

We just built the best collision prediction model on the planet. BADAS 2.0: 99.4% AP. Built on V-JEPA2, Yann LeCun's physical AI architecture. A true world model that understands reality, not just the road. Explainable. Generalizes beyond driving. Runs from cloud to edge. Our 22M model beats NVIDIA's 2B Cosmos. We published the benchmarks. We're inviting comparison. Safer roads, safer cars. That's the point. Run your own videos on BADAS 2.0, link in the first reply.

Nexar

1,841,669 views • 2 months ago

We are excited to share #OceanWatch, a new 40-minute film with mesmerizing #DeepSea footage from the ground-breaking discoveries on Research Vessel #FalkorToo in 2023. Made with the always amazing Leo Richards (Natural World Facts). Trailer attached, full video here:

We are excited to share #OceanWatch, a new 40-minute film with mesmerizing #DeepSea footage from the ground-breaking discoveries on Research Vessel #FalkorToo in 2023. Made with the always amazing Leo Richards (Natural World Facts). Trailer attached, full video here:

Schmidt Ocean

10,904 views • 2 years ago

We took a robot to RSS in LA running our new Gemini Robotics On-Device VLA model. People interacted with the model with new objects and instructions in a brand new environment and the results were amazing!

Ayzaan Wahid

19,669 views • 1 year ago

We Sequoia Capital are thrilled to announce our investment into Decart Today they’re launching a “warm-up” called Oasis This is a fully playable version of Minecraft WITH NO GAME ENGINE, it’s purely a video model rendering pixels in real time

We Sequoia Capital are thrilled to announce our investment into Decart Today they’re launching a “warm-up” called Oasis This is a fully playable version of Minecraft WITH NO GAME ENGINE, it’s purely a video model rendering pixels in real time

Shaun Maguire

739,654 views • 1 year ago

SAM 3 tackles a challenging problem in vision: unifying a model architecture for detection and tracking. Christoph, a researcher on SAM 3, shares how the team made it possible. 🔗 Read the SAM 3 research paper:

SAM 3 tackles a challenging problem in vision: unifying a model architecture for detection and tracking. Christoph, a researcher on SAM 3, shares how the team made it possible. 🔗 Read the SAM 3 research paper:

AI at Meta

13,803 views • 7 months ago

🎉 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:

🎉 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 • 1 year ago

We’re on a path to video of any kind being imagined by a model in real-time. Because it’s real-time generated, each video becomes fully interactive & personalized. Type or speak into the model, and the video will respond in real-time. A revolutionary form of media is emerging!

We’re on a path to video of any kind being imagined by a model in real-time. Because it’s real-time generated, each video becomes fully interactive & personalized. Type or speak into the model, and the video will respond in real-time. A revolutionary form of media is emerging!

Oliver Cameron

67,924 views • 11 months ago

A gymnast from our brother country Azerbaijan just did a triple triple, an insane impossible feat. I think this is the first time in the world in competition

A gymnast from our brother country Azerbaijan just did a triple triple, an insane impossible feat. I think this is the first time in the world in competition

Habibullah Khan

243,625 views • 7 months ago

We just published a peer-reviewed milestone study in Nature, demonstrating a significant advancement in quantum computing systems using our commercial-grade annealing-based quantum computer with over 5,000 qubits. The study provides evident of quantum annealing's unrivaled performance. Check out our blog and video to learn more about this groundbreaking research! Read the blog here: #QuantumComputing #DWave #QuantumAnnealing #Quantum

We just published a peer-reviewed milestone study in Nature, demonstrating a significant advancement in quantum computing systems using our commercial-grade annealing-based quantum computer with over 5,000 qubits. The study provides evident of quantum annealing's unrivaled performance. Check out our blog and video to learn more about this groundbreaking research! Read the blog here: #QuantumComputing #DWave #QuantumAnnealing #Quantum

D-Wave

10,679 views • 3 years ago