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.

Real-time generation isn’t about predicting the next pixel, it requires understanding the structure and context of a 3D world. That’s the shift. Read more about our real-time game-native diffusion model on our blog. Moonlake's Reverie v0.1.0

Moonlake

6,987 subscribers

14,439 views • 6 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

Meet 3D Gaussian Splatting - a 3D AI breakthrough that’s changing the game for real-time 3D rendering. It generates 3D world with state-of-the-art visuals at fast speeds: 100+ fps at 1080p. Here’s the magic behind it:

Meet 3D Gaussian Splatting - a 3D AI breakthrough that’s changing the game for real-time 3D rendering. It generates 3D world with state-of-the-art visuals at fast speeds: 100+ fps at 1080p. Here’s the magic behind it:

el.cine

60,115 views • 1 year ago

Game generation → diffusion output, end-to-end. From prompt to scene: a moon-like environment created in our engine and reskinned into flexible media assets. Built on our web app.

Game generation → diffusion output, end-to-end. From prompt to scene: a moon-like environment created in our engine and reskinned into flexible media assets. Built on our web app.

Moonlake

20,014 views • 5 months ago

The world of Pengu: Understanding the fundamentals to our shared future. Track Pengu's mindshare, holder count, followers, big brand partnerships, and more, all in real time, updated every second.

Pudgy Penguins

493,323 views • 11 months ago

This is the real price of Ukrainian grain. Remember it next time you read about who buys the stolen grain Russia sells. Video: Natalia Dobroliezha

This is the real price of Ukrainian grain. Remember it next time you read about who buys the stolen grain Russia sells. Video: Natalia Dobroliezha

Maria Avdeeva

15,542 views • 23 days ago

Video generation is powerful but too slow for real-world robotic tasks. How can we enable both video and action generation while ensuring real-time policy inference? Check out our work on the Unified Video Action Model (UVA) to find out! (1/7)

Video generation is powerful but too slow for real-world robotic tasks. How can we enable both video and action generation while ensuring real-time policy inference? Check out our work on the Unified Video Action Model (UVA) to find out! (1/7)

Shuang Li

67,367 views • 1 year ago

As announced in partnership with NVIDIA at CES, we’re excited to introduce Stable Point Aware 3D (SPAR3D), setting a new standard in 3D generation. Ideal for running on NVIDIA RTX AI PCs, SPAR3D enables real-time editing and complete structure generation of 3D objects from a single image in under a second. You can download the weights on Hugging Face and code on GitHub, or access the model through the Stability AI API. Learn more here: (1/3)

As announced in partnership with NVIDIA at CES, we’re excited to introduce Stable Point Aware 3D (SPAR3D), setting a new standard in 3D generation. Ideal for running on NVIDIA RTX AI PCs, SPAR3D enables real-time editing and complete structure generation of 3D objects from a single image in under a second. You can download the weights on Hugging Face and code on GitHub, or access the model through the Stability AI API. Learn more here: (1/3)

Stability AI

181,402 views • 1 year ago

Power Surge is less than 24h away! Read more about the upcoming update on our latest Dev Blog ⚡️

Power Surge is less than 24h away! Read more about the upcoming update on our latest Dev Blog ⚡️

Rust Console Edition

307,076 views • 3 years ago

Web3 gaming isn’t ready for what’s coming. AI wallets. Real-time player intel. On-chain smarts baked into every move. This is the brain of the next generation 🧠🐳 CCN Read the full article here 📖

Web3 gaming isn’t ready for what’s coming. AI wallets. Real-time player intel. On-chain smarts baked into every move. This is the brain of the next generation 🧠🐳 CCN Read the full article here 📖

Bluwhale

21,861 views • 1 year ago

We tested it for the first time yesterday and can hardly contain our excitement for what AgBr V1.4 is set to become — the level of film emulation is about to get even more real. + V1.3 launches on Monday — and it is packed.

We tested it for the first time yesterday and can hardly contain our excitement for what AgBr V1.4 is set to become — the level of film emulation is about to get even more real. + V1.3 launches on Monday — and it is packed.

Nuevo.Tokyo™

14,367 views • 11 months ago

Lukashenko became president of Belarus for the seventh time. "Half the world dreams of our dictatorship – a dictatorship of real deeds and the interests of our people," Lukashenko said during inauguration.

Lukashenko became president of Belarus for the seventh time. "Half the world dreams of our dictatorship – a dictatorship of real deeds and the interests of our people," Lukashenko said during inauguration.

Anton Gerashchenko

74,906 views • 1 year ago

Real-time conversations for game-time decisions on #Pixel10 Share your 📷 in Google Gemini Live & get a highlighted solution for even more precise responses—like the perfect ingredient swap 🍽️¹ Check it out on Pixel 10, Pixel 10 Pro, & Pixel 10 Pro Fold:

Real-time conversations for game-time decisions on #Pixel10 Share your 📷 in Google Gemini Live & get a highlighted solution for even more precise responses—like the perfect ingredient swap 🍽️¹ Check it out on Pixel 10, Pixel 10 Pro, & Pixel 10 Pro Fold:

Made by Google

25,326 views • 9 months ago

We refreshed our logo to better reflect what we are building: multimodal world models that simulate environments, predict outcomes, and enable planning over long horizons. We kept the moon from our original mark and evolved it into a symbol of depth, generation, and evolving worlds.

Moonlake

12,664 views • 3 months ago

Matrix-Game 2.0 — The FIRST open-source, real-time, long-sequence interactive world model Last week, DeepMind's Genie 3 shook the AI world with real-time interactive world models. But... it wasn't open-sourced. Today, Matrix-Game 2.0 changed the game. 🚀 25FPS. Minutes-long interaction. Fully open-source.

Matrix-Game 2.0 — The FIRST open-source, real-time, long-sequence interactive world model Last week, DeepMind's Genie 3 shook the AI world with real-time interactive world models. But... it wasn't open-sourced. Today, Matrix-Game 2.0 changed the game. 🚀 25FPS. Minutes-long interaction. Fully open-source.

Skywork

1,398,646 views • 10 months ago

It’s up to all of us to get on the same page about consent, for the benefit of the next generation. Learning, understanding and talking about consent can’t wait.

It’s up to all of us to get on the same page about consent, for the benefit of the next generation. Learning, understanding and talking about consent can’t wait.

Australian Government

8,093,634 views • 2 years ago

That’s a wrap on Day 2 at #ConsensusHK by CoinDesk! @roeisoud37097 & @DagaCMO were on the ground, connecting with Builders and Web3 leaders while sharing more about our vision at Incentiv. Great conversations, solid connections, and plenty of pictures to remember it all. Until next time 🤝

That’s a wrap on Day 2 at #ConsensusHK by CoinDesk! @roeisoud37097 & @DagaCMO were on the ground, connecting with Builders and Web3 leaders while sharing more about our vision at Incentiv. Great conversations, solid connections, and plenty of pictures to remember it all. Until next time 🤝

Incentiv

39,380 views • 1 year ago

DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion TL;DR: Create 3/4DGS from Video Diffusion Note: Some first inference code released (not all yet). Contributions (cited): • We present DimensionX, a novel framework for generating photorealistic 3D and 4D scenes from only a single image using controllable video diffusion. • We propose ST-Director, which decouples the spatial and temporal priors in video diffusion models by learning (spatial and temporal) dimension-aware modules with our curated datasets. We further enhance the hybriddimension control with a training-free composition approach according to the essence of video diffusion denoising process. • To bridge the gap between video diffusion and real-world scenes, we design a trajectory-aware mechanism for 3D generation and an identity-preserving denoising approach for 4D generation, enabling more realistic and controllable scene synthesis. • Extensive experiments manifest that our DimensionX delivers superior performance in video, 3D, and 4D generation compared with baseline methods.

DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion TL;DR: Create 3/4DGS from Video Diffusion Note: Some first inference code released (not all yet). Contributions (cited): • We present DimensionX, a novel framework for generating photorealistic 3D and 4D scenes from only a single image using controllable video diffusion. • We propose ST-Director, which decouples the spatial and temporal priors in video diffusion models by learning (spatial and temporal) dimension-aware modules with our curated datasets. We further enhance the hybriddimension control with a training-free composition approach according to the essence of video diffusion denoising process. • To bridge the gap between video diffusion and real-world scenes, we design a trajectory-aware mechanism for 3D generation and an identity-preserving denoising approach for 4D generation, enabling more realistic and controllable scene synthesis. • Extensive experiments manifest that our DimensionX delivers superior performance in video, 3D, and 4D generation compared with baseline methods.

MrNeRF

17,028 views • 1 year ago

World modeling and imitation learning have largely been considered two disparate worlds. In our recent work, Unified World Models, just accepted to #RSS2025, Chuning Zhu provides a dead-simple unifying solution: just train a joint diffusion model over actions and future states, but with *decoupled* diffusion time steps across these modalities. Manipulating these decoupled time steps then allows for marginalization or conditioning on actions or states; a single model can serve as a policy, forward dynamics model, video prediction model, or inverse dynamics model by simply setting diffusion timesteps carefully. The resulting model can leverage video datasets along with robot training data much more effectively, and shows improved robustness, generalization, and flexibility. This is exciting because it is frustratingly simple, scalable, and shows strong improvement on real-world robotics problems. Please refer to Chuning Zhu 's excellent thread for more details! More details/code can be found on our website and in the paper -

World modeling and imitation learning have largely been considered two disparate worlds. In our recent work, Unified World Models, just accepted to #RSS2025, Chuning Zhu provides a dead-simple unifying solution: just train a joint diffusion model over actions and future states, but with decoupled diffusion time steps across these modalities. Manipulating these decoupled time steps then allows for marginalization or conditioning on actions or states; a single model can serve as a policy, forward dynamics model, video prediction model, or inverse dynamics model by simply setting diffusion timesteps carefully. The resulting model can leverage video datasets along with robot training data much more effectively, and shows improved robustness, generalization, and flexibility. This is exciting because it is frustratingly simple, scalable, and shows strong improvement on real-world robotics problems. Please refer to Chuning Zhu 's excellent thread for more details! More details/code can be found on our website and in the paper -

Abhishek Gupta

11,388 views • 1 year ago

We’re excited to announce the launch of our new website! Visit to: • Access real-time $DIME S2 trading data • Explore live market stats with historical trades • View real-time orderbooks and charts • Learn more about our rules and services S2 points only for now - S1 coming soon. Stay connected and explore the future of $DIME trading with Paradex OTC.

We’re excited to announce the launch of our new website! Visit to: • Access real-time $DIME S2 trading data • Explore live market stats with historical trades • View real-time orderbooks and charts • Learn more about our rules and services S2 points only for now - S1 coming soon. Stay connected and explore the future of $DIME trading with Paradex OTC.

CrossdeskOTC

24,628 views • 5 months ago

Announcing AlphaFold 3: our state-of-the-art AI model for predicting the structure and interactions of all life’s molecules. 🧬 Here’s how we built it with Isomorphic Labs and what it means for biology. 🧵

Announcing AlphaFold 3: our state-of-the-art AI model for predicting the structure and interactions of all life’s molecules. 🧬 Here’s how we built it with Isomorphic Labs and what it means for biology. 🧵

Google DeepMind

1,467,109 views • 2 years ago