Decart's banner

Decart

@DecartAI • 20,568 subscribers

We are an AI research lab building Realtime world and video models for anything from gaming and entertainment to physical AI

Shorts

DecartXR: AI meets XR "welcome to the Oasis" 🥽 An open-source app that lets you transform your world in real time, just by speaking. A new way to create, build, and imagine — live. See below how to build with this tech (and a demo on Meta Quest or web) 👇🏻

DecartXR: AI meets XR "welcome to the Oasis" 🥽 An open-source app that lets you transform your world in real time, just by speaking. A new way to create, build, and imagine — live. See below how to build with this tech (and a demo on Meta Quest or web) 👇🏻

4,298,946 views

Your Live Stream is ALIVE Meet DecartStream - Realtime editing for streamers. No installs, no setup. Just instant transformations on any streaming platform. See below how to use it now.. right on time for TwitchCon 🧵

Your Live Stream is ALIVE Meet DecartStream - Realtime editing for streamers. No installs, no setup. Just instant transformations on any streaming platform. See below how to use it now.. right on time for TwitchCon 🧵

1,427,621 views

Our video editing model Lucy-Edit just got way better. 2× faster, half the price (and open source). More control, faster performance, and seamless results.

Our video editing model Lucy-Edit just got way better. 2× faster, half the price (and open source). More control, faster performance, and seamless results.

814,369 views

We are building “Open Source Nano Banana for Video” - here is open source demo v0.1 We are open sourcing Lucy Edit, the first foundation model for text-guided video editing! Get the model on Hugging Face 🤗, API on @FAL, and nodes on ComfyUI 🧵

We are building “Open Source Nano Banana for Video” - here is open source demo v0.1 We are open sourcing Lucy Edit, the first foundation model for text-guided video editing! Get the model on Hugging Face 🤗, API on @FAL, and nodes on ComfyUI 🧵

413,513 views

New drop: Decart Lip Sync API. Real-time lip sync for any avatar. Stream audio → get perfectly synced video frames with low latency. No uncanny lag. No pre-rendering. Just living pixels that move when your model speaks. 🧵

43,494 views

Speed kills quality? Only if you suck. Meet Lucy-14B, the fastest large I2V model you’ve ever seen. Available now on fal.

Speed kills quality? Only if you suck. Meet Lucy-14B, the fastest large I2V model you’ve ever seen. Available now on fal.

35,706 views

Building with video AI now comes with Realtime endpoints. We’re launching the Decart API Platform - the fastest video API ever. Here are some weekend project ideas 👇

Building with video AI now comes with Realtime endpoints. We’re launching the Decart API Platform - the fastest video API ever. Here are some weekend project ideas 👇

31,615 views

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

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)! 🧵

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)! 🧵

2,332,507 views • 9 months ago

Excited to share that we’ve raised $300M in our Series B round, led by Radical Ventures, bringing our total funding to more than $450M, with leading technology companies joining as both customers and investors. We continue accelerating the path to AGI through our two core pillars: ultra-optimized infrastructure for AI workloads, and realtime world models built on top of it. Today, we’re also launching DOS (Decart Optimization Stack) 2.0 – our next-generation inference and training platform, delivering over 1,600 tokens per second for agentic inference and over 100 FPS for world models across major hardware platforms. Alongside DOS, we will launch new versions of our world models in the coming weeks: Lucy, for immersive realtime experiences, and Oasis, for physical AI. Grateful to our partners, customers, and backers across media & entertainment, Physical AI, chips, hyperscalers, and the broader AI ecosystem. Radical Ventures, Adobe, Alpha Partners, Amazon and Amazon Web Services, Atreides Management, LP, Benchmark, eBay, NVIDIA, Sequoia Capital, Toyota USA, @valorep, oren zeev; Andrej Karpathy, Michael Eisner, Yamauchi-No.10 Family Office, Moritz Baier-Lentz and more. We made a film for this moment with Decart CEO Dean Leitersdorf and Moritz Baier-Lentz - a look at the company, the technology, and what comes next.

Excited to share that we’ve raised $300M in our Series B round, led by Radical Ventures, bringing our total funding to more than $450M, with leading technology companies joining as both customers and investors. We continue accelerating the path to AGI through our two core pillars: ultra-optimized infrastructure for AI workloads, and realtime world models built on top of it. Today, we’re also launching DOS (Decart Optimization Stack) 2.0 – our next-generation inference and training platform, delivering over 1,600 tokens per second for agentic inference and over 100 FPS for world models across major hardware platforms. Alongside DOS, we will launch new versions of our world models in the coming weeks: Lucy, for immersive realtime experiences, and Oasis, for physical AI. Grateful to our partners, customers, and backers across media & entertainment, Physical AI, chips, hyperscalers, and the broader AI ecosystem. Radical Ventures, Adobe, Alpha Partners, Amazon and Amazon Web Services, Atreides Management, LP, Benchmark, eBay, NVIDIA, Sequoia Capital, Toyota USA, @valorep, oren zeev; Andrej Karpathy, Michael Eisner, Yamauchi-No.10 Family Office, Moritz Baier-Lentz and more. We made a film for this moment with Decart CEO Dean Leitersdorf and Moritz Baier-Lentz - a look at the company, the technology, and what comes next.

92,953 views • 16 days ago

Restyle your live video while it is playing. Introducing LSD v2 - our new realtime flagship model. It’s illegally good. Try it now - free for the next 72 hours!

Restyle your live video while it is playing. Introducing LSD v2 - our new realtime flagship model. It’s illegally good. Try it now - free for the next 72 hours!

1,043,347 views • 6 months ago

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!):

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!):

1,007,542 views • 10 months ago

Drag, Drop and Try it live That's just a small glimpse of what’s possible when AI runs in Realtime, powered by Lucy 2.0. What else can you build?

Drag, Drop and Try it live That's just a small glimpse of what’s possible when AI runs in Realtime, powered by Lucy 2.0. What else can you build?

311,144 views • 3 months ago

Feature drop: "Custom Worlds" You can now add your own starting image to Oasis and the AI will morph it into your new world Go to the contest-1 channel on the Discord server to submit your creations To the community: we seriously can't wait to see what you create - love your energy!

Feature drop: "Custom Worlds" You can now add your own starting image to Oasis and the AI will morph it into your new world Go to the contest-1 channel on the Discord server to submit your creations To the community: we seriously can't wait to see what you create - love your energy!

63,107 views • 1 year ago

You can plug real-time video models directly into gameplay. Built with v0 on Vercel, vibe-coded with @geminiapp Pro 3. This Flight Simulator pipes Three.js into Decart LSD v2, turning it into an AI video renderer with live prompts, VFX, lighting, and shadows.

You can plug real-time video models directly into gameplay. Built with v0 on Vercel, vibe-coded with @geminiapp Pro 3. This Flight Simulator pipes Three.js into Decart LSD v2, turning it into an AI video renderer with live prompts, VFX, lighting, and shadows.

21,639 views • 6 months ago

Real-time AI video hits re:Invent. Dean Leitersdorf shows our models running fully live on Trainium 3 - 3.8× FPS, 89% utilization. This is a new era of visual intelligence.

Real-time AI video hits re:Invent. Dean Leitersdorf shows our models running fully live on Trainium 3 - 3.8× FPS, 89% utilization. This is a new era of visual intelligence.

17,155 views • 6 months ago

No more content to load