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.

Capture your space. Create worlds. Use Marble 1.1 to reconstruct real-world locations from a few images, then restyle them however you want. Go from a real place to a custom persistent 3D world in minutes.

World Labs

109,938 subscribers

65,762 views • 5 months ago •via X (Twitter)

Arts Education Science & Technology

Anya Rossi• Live Now

Private livecam show

16 Comments

World Labs5 months ago

Once you have the Gaussian splat file, you can view it in a headset to bridge the digital and physical. We took the reconstructed scene and overlaid it in mixed reality. You can walk through the restyled space and see the geometry align almost perfectly with the real world.

World Labs5 months ago

We’re building Marble to be the core of creative workflows. Using foundational world models that understand the 3D world, Marble provides a canvas for storytelling, simulation, and design to transform how we imagine digital environments. Learn more:

cristina brodu5 months ago

the dream of every interior designer!!

World Labs5 months ago

Yes! 🌎 😍

cristina brodu5 months ago

Please be soon available in the UK @theworldlabs! I have surreal & real new words to create but I’m based in London!

Verdo5 months ago

Are we really so bored with the real world that we need to perfectly clone it into the metaverse? What's next, virtual cubicles?

Cryptexis5 months ago

@drfeifei what is the point of this if I just „reskin“ the interior instead of suggesting new concepts?

Zara Techie5 months ago

Crafting limitless spaces from a few images.

Altiam Kabir5 months ago

Turning real glimpses into immersive worlds.

Carlos Roldán5 months ago

This looks amazing. How much $$$ would I spent approx. to scan all 11 spaces in my house and test ~5 ideas on each? Is it possible to interconnect them once I'm happy with each version?

Ava Grace5 months ago

Real-world capture, limitless worlds ahead.

Sumon Kabir5 months ago

Astounding workflow—turns places into vivid realms.

AI PlanetX5 months ago

Transforms spaces into living, customizable worlds

Verdo5 months ago

Generative AI can already output complex 3D models from text prompts in seconds. This 'from a few images' approach feels like last year's tech trying to catch up to real innovation.

Sanky5 months ago

From a few snaps to a full 3D world?! 🤯🏙️ Marble 1.1 is wild!

Captain Walker5 months ago

@drfeifei Too bad you don’t get to actually own what you render in Marble. Sucks and such a shame. Fei Fei was legitimately for the people until the money landed. She could care less about humanity before a dollar. She does nothing to support humanity based platforms. She’s not true XR

Related Videos

Lay out a scene in any 3D tool, then bring your world to life inside Marble! Go from basic layout → fully realized world in minutes 🌎

Lay out a scene in any 3D tool, then bring your world to life inside Marble! Go from basic layout → fully realized world in minutes 🌎

World Labs

88,386 views • 6 months ago

The World API is live. Generate persistent, explorable 3D worlds from text, images, and video. Integrate them directly into your products.

The World API is live. Generate persistent, explorable 3D worlds from text, images, and video. Integrate them directly into your products.

World Labs

662,829 views • 8 months ago

Marble is the first product from World Labs and is powered by our multimodal world model, which lets anyone create high-fidelity, persistent 3D worlds from just a single image, video, text prompt, or 3D layout. Read more at

Marble is the first product from World Labs and is powered by our multimodal world model, which lets anyone create high-fidelity, persistent 3D worlds from just a single image, video, text prompt, or 3D layout. Read more at

World Labs

117,588 views • 10 months ago

Turned my real world 360 images into 3d scenes with World Labs. You can use the built-in editing tools to stitch them together into large-scale 3d worlds - then use them as virtual set for your AI videos, games and VR experiences. The holodeck is much closer than you think.

Turned my real world 360 images into 3d scenes with World Labs. You can use the built-in editing tools to stitch them together into large-scale 3d worlds - then use them as virtual set for your AI videos, games and VR experiences. The holodeck is much closer than you think.

Bilawal Sidhu

27,928 views • 10 months ago

You can now copy & paste the real world, with hyper-realistic detail. All with just a $299 headset. With Hyperscape you can capture your real-world space in just minutes, then creates an immersive, true-to-life digital replica that you can visit from anywhere. Check the thread for some ridiculously good scans 👇

You can now copy & paste the real world, with hyper-realistic detail. All with just a $299 headset. With Hyperscape you can capture your real-world space in just minutes, then creates an immersive, true-to-life digital replica that you can visit from anywhere. Check the thread for some ridiculously good scans 👇

Jake Steinerman 🌎

29,722 views • 1 year ago

The Ring (Montreal) — Dormant Memories series New alternate scene, and an iteration on the UX and flow. Starting from a volumetric capture of a real location in Montreal, reconstructed as 3D Gaussian Splats, I then used World Labs' Marble to generate alternate versions of that same space. Running in real time using spark. #GaussianSplatting #3DGS #pointcloud #sparkjs #threejs

The Ring (Montreal) — Dormant Memories series New alternate scene, and an iteration on the UX and flow. Starting from a volumetric capture of a real location in Montreal, reconstructed as 3D Gaussian Splats, I then used World Labs' Marble to generate alternate versions of that same space. Running in real time using spark. #GaussianSplatting #3DGS #pointcloud #sparkjs #threejs

Hugues Bruyère

34,524 views • 6 months ago

New open-source 3D world-generation model. I'm rendering a couple of worlds in the video, so check it out. You'll find the GitHub and the Hugging Face links to the model below. This is a multi-modal world model that you can use for a bunch of things: • To generate new worlds • To reconstruct worlds • To simulate 3D interactive worlds from a prompt, images, or a video You can edit the 3D outputs in Unity and Unreal Engine (they export as meshes, 3DGS files, and point clouds). You can also generate 3D characters in the world and walk around. Pretty fun stuff!

New open-source 3D world-generation model. I'm rendering a couple of worlds in the video, so check it out. You'll find the GitHub and the Hugging Face links to the model below. This is a multi-modal world model that you can use for a bunch of things: • To generate new worlds • To reconstruct worlds • To simulate 3D interactive worlds from a prompt, images, or a video You can edit the 3D outputs in Unity and Unreal Engine (they export as meshes, 3DGS files, and point clouds). You can also generate 3D characters in the world and walk around. Pretty fun stuff!

Santiago

65,446 views • 5 months ago

RTFM (Real-Time Frame Model) explores real-time, interactive frame generation from images, producing new views on the fly without explicit 3D. It differs from Marble, which targets high-fidelity persistent worlds (3DGS). We’re interested in how ideas from both might connect 🌎

RTFM (Real-Time Frame Model) explores real-time, interactive frame generation from images, producing new views on the fly without explicit 3D. It differs from Marble, which targets high-fidelity persistent worlds (3DGS). We’re interested in how ideas from both might connect 🌎

World Labs

74,757 views • 7 months ago

testing astra's parametric modeling capabilities by asking it to reconstruct these marble maze pieces from reference photos, and then use them in threejs to make a marble maze builder with box3d physics.

testing astra's parametric modeling capabilities by asking it to reconstruct these marble maze pieces from reference photos, and then use them in threejs to make a marble maze builder with box3d physics.

Codetaur

85,036 views • 15 days ago

Just one of the projects you'll build during this free online workshop on July 8th, 11 AM PT 👉 You will learn: - how to create and edit #3D worlds with Marble - run detection on synthetic splats to add interactivity, - reconstruct real-world spaces with XGRIDS workflows, - deploy splat worlds into #WebXR, #Unity and #Unreal

Just one of the projects you'll build during this free online workshop on July 8th, 11 AM PT 👉 You will learn: - how to create and edit #3D worlds with Marble - run detection on synthetic splats to add interactivity, - reconstruct real-world spaces with XGRIDS workflows, - deploy splat worlds into #WebXR, #Unity and #Unreal

Gabriele Romagnoli

11,750 views • 3 months ago

Generate persistent 3D worlds from a single image, bigger and better than ever! We’re excited to share our latest results and invite you to try out our world generation model in a limited beta preview.

Generate persistent 3D worlds from a single image, bigger and better than ever! We’re excited to share our latest results and invite you to try out our world generation model in a limited beta preview.

World Labs

835,786 views • 1 year ago

From a single image to a full robotics simulation. 360 image → Marble → 3D environment → Robotics sim This is how we scale world creation for embodied AI with Lightwheel, turning lightweight capture into simulation-ready environments in minutes, not weeks.

From a single image to a full robotics simulation. 360 image → Marble → 3D environment → Robotics sim This is how we scale world creation for embodied AI with Lightwheel, turning lightweight capture into simulation-ready environments in minutes, not weeks.

World Labs

46,239 views • 8 months ago

“Squid Fleet” juxtaposes fictionalized narration with real footage from our trips boarding squid vessels to capture a strange world that few outsiders get to see:

“Squid Fleet” juxtaposes fictionalized narration with real footage from our trips boarding squid vessels to capture a strange world that few outsiders get to see:

Ian Urbina

15,175 views • 3 years ago

Real human motion inside a generated world hits different ⚡️👀 We built a world with Marble by World Labs, reconstructed it into a 3D environment with Jawset Postshot, then dropped in multiple SMPL characters with motion from Meshcapade Me and ran it in Unreal Engine 🎮 No suits. No markers. Just real movement colliding with synthetic space 🧠 It feels wrong. That’s the point. #MarkerlessMocap #GaussianSplatting #DigitalHumans

Real human motion inside a generated world hits different ⚡️👀 We built a world with Marble by World Labs, reconstructed it into a 3D environment with Jawset Postshot, then dropped in multiple SMPL characters with motion from Meshcapade Me and ran it in Unreal Engine 🎮 No suits. No markers. Just real movement colliding with synthetic space 🧠 It feels wrong. That’s the point. #MarkerlessMocap #GaussianSplatting #DigitalHumans

Meshcapade

10,250 views • 9 months ago

Heading to Google in LA today to meet with a few major studios and show them Preview A feature everyone loves is this ability to generate a world in canvas Step into it like a real location scout, shoot your new angles, and turn them into high fidelity images Add your characters into the shots and you've got a very very effective tool for shooting custom scene coverage in minutes.

Heading to Google in LA today to meet with a few major studios and show them Preview A feature everyone loves is this ability to generate a world in canvas Step into it like a real location scout, shoot your new angles, and turn them into high fidelity images Add your characters into the shots and you've got a very very effective tool for shooting custom scene coverage in minutes.

Kyle Salazar

53,617 views • 7 months ago

How do you go from scanning a real-world space → using it in an app, workflow, or environment? Our product team walks through Scaniverse step-by-step, from capturing spaces to generating production-ready 3D assets and enabling precise, real-world positioning. In the first video, Senior Product Manager, Bec Maxworth, walks through your entry point into Scaniverse from signing up to getting started so you can start building high-fidelity 3D models in minutes. Dive into the full walkthrough here: #NianticSpatial #Scaniverse #Reconstruction #VPS #GeospatialAI #AI #PhysicalAI

How do you go from scanning a real-world space → using it in an app, workflow, or environment? Our product team walks through Scaniverse step-by-step, from capturing spaces to generating production-ready 3D assets and enabling precise, real-world positioning. In the first video, Senior Product Manager, Bec Maxworth, walks through your entry point into Scaniverse from signing up to getting started so you can start building high-fidelity 3D models in minutes. Dive into the full walkthrough here: #NianticSpatial #Scaniverse #Reconstruction #VPS #GeospatialAI #AI #PhysicalAI

Niantic Spatial 🌎

10,739 views • 5 months ago

🇳🇱🗽 This is probably the closest you can get to walking around in New Amsterdam in 1670 (current day New York) A 3d world made with World Labs from the AI render below which is based on a real map from then!

🇳🇱🗽 This is probably the closest you can get to walking around in New Amsterdam in 1670 (current day New York) A 3d world made with World Labs from the AI render below which is based on a real map from then!

@levelsio

597,738 views • 1 year ago

World Labs co-founder Justin Johnson predicts a real-to-sim-to-real future where Atlas could train a robot for any new environment in minutes using just 5 photos from your phone: "One is this notion of fully in-context learning. Maybe I've got a robotics foundation model, then I can demonstrate the robot once how a task should be performed, and that's enough for the robot to figure out." "Another version is real to sim to real. Maybe I've got my pre-trained robotics foundation model, but I want to adapt it to this particular environment, like this studio, this table, moving this microphone around." "There's a version where you could come in here and take just a couple casual videos with your phone or a couple images with your phone, use Atlas to reconstruct the space, and now stage all kinds of robotics interactions in this studio space." "If you could lower the barrier to doing that, you could do it in five minutes to take five photos, upload it to Atlas, have it generate a simulation, maybe describe in natural language what kind of task you want the robot to do, have an agent go build that simulation for you, RL fine-tune your general purpose robotics foundation model, and now you've got a robot maybe in the span of a couple minutes that could come in and is perfectly adapted to this space." World Labs

World Labs co-founder Justin Johnson predicts a real-to-sim-to-real future where Atlas could train a robot for any new environment in minutes using just 5 photos from your phone: "One is this notion of fully in-context learning. Maybe I've got a robotics foundation model, then I can demonstrate the robot once how a task should be performed, and that's enough for the robot to figure out." "Another version is real to sim to real. Maybe I've got my pre-trained robotics foundation model, but I want to adapt it to this particular environment, like this studio, this table, moving this microphone around." "There's a version where you could come in here and take just a couple casual videos with your phone or a couple images with your phone, use Atlas to reconstruct the space, and now stage all kinds of robotics interactions in this studio space." "If you could lower the barrier to doing that, you could do it in five minutes to take five photos, upload it to Atlas, have it generate a simulation, maybe describe in natural language what kind of task you want the robot to do, have an agent go build that simulation for you, RL fine-tune your general purpose robotics foundation model, and now you've got a robot maybe in the span of a couple minutes that could come in and is perfectly adapted to this space." World Labs

MTS

25,204 views • 27 days ago

Adobe is entering the image-to-3D game! Their new method, LRM, can create high-fidelity 3D meshes from a single image in just 5 seconds 🔥 It's trained on 1 million objects and is able to generate objects from real-world images and generative AI models.

Adobe is entering the image-to-3D game! Their new method, LRM, can create high-fidelity 3D meshes from a single image in just 5 seconds 🔥 It's trained on 1 million objects and is able to generate objects from real-world images and generative AI models.

Dreaming Tulpa 🥓👑

270,942 views • 2 years ago

i built an app that converts any space into a digital clone in minutes as the founder of Teleport - the only iphone app that can capture high-quality 360° panoramas - i already had the perfect input when World Labs released their 3d reconstruction api 📍 first test - a co-working space in chiang mai 🇹🇭 the flow: 1. capture 16 ultra-wide photos 2. stitch into a 360° equirectangular image 3. reconstruct a fully navigable 3d environment via World Labs api there’s something profound about exploring these 3d worlds. it brings you back in a way photos never could.

i built an app that converts any space into a digital clone in minutes as the founder of Teleport - the only iphone app that can capture high-quality 360° panoramas - i already had the perfect input when World Labs released their 3d reconstruction api 📍 first test - a co-working space in chiang mai 🇹🇭 the flow: 1. capture 16 ultra-wide photos 2. stitch into a 360° equirectangular image 3. reconstruct a fully navigable 3d environment via World Labs api there’s something profound about exploring these 3d worlds. it brings you back in a way photos never could.

Martin Maly

5,158,816 views • 7 months ago