Ian Curtis

@XRarchitect • 25,740 subscribers

Design @theworldlabs

Shorts

3,033,209 views

429,724 views

430,950 views

263,939 views

638,428 views

251,433 views

395,285 views

626,660 views

145,682 views

431,977 views

127,448 views

175,940 views

115,596 views

236,605 views

117,752 views

61,737 views

88,236 views

78,938 views

80,496 views

46,469 views

Videos

sweetdream.ai

Watch Anya Live

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

Private Show

Join now for exclusive access

Free preview available • Premium content

87,436 views • 3 days ago

104,494 views • 4 days ago

444,221 views • 3 months ago

97,700 views • 1 month ago

29,698 views • 12 days ago

38,984 views • 19 days ago

27,759 views • 17 days ago

103,845 views • 2 months ago

66,039 views • 2 months ago

569,625 views • 2 years ago

533,333 views • 2 years ago

76,943 views • 3 months ago

46,647 views • 2 months ago

48,700 views • 2 months ago

94,784 views • 5 months ago

44,540 views • 2 months ago

54,750 views • 5 months ago

51,726 views • 6 months ago

77,361 views • 1 year ago

Live Cam

Ian Curtis

Shorts

re-masked my living room with the Quest3, transforming it into a old-school Game Boy aesthetic.

Testing off-axis projection demo. Basic scene layout in Blender glb -&gt; detailed splat via World Labs Three.js for engine MediaPipe for face tracking Next step is to add a character you can move around in the environment

15mb gaussian splat generated from a single Midjourney image running extremely smooth on the web. 2026 will be the year for world models.

Created an off-axis projection demo using mediapipe for face tracking, threejs and a 3D scanned shoe. Try it out yourself…

Just tested Grok for the first time, and It’s surprisingly solid at coding compared to other AI models. I used it to generate the logic for this web based 3D augmented reality Pong game, and it handled it well. This took a bit of back and forth but still pretty quick.

Visualizing my re-designed living room in 3D Nano banana -&gt; World Labs -&gt; WebAR (threejs) Each of these gaussian splats are only 1.5 mb in size (.spz file type)

Created this game demo over the weekend without writing a single line of code! Built via bolt (Claude Sonnet 3.7) and powered by R3f + three.js Try it yourself - dodge enemies with real-time physics. Here's how I created the game + a cloneable character controller project 1/7

Reimagining my living room with a classic Game Boy style using augmented reality and VPS.

First test stitching together World Labs generations to build an interactive fps experience. Every environment you see was generated from single images. How it was built:

AI-Generated QR Code Augmented Reality V2.0 Mars Test it out yourself in thread 👀

Been experimenting with a similar technique lately Midjourney —&gt; Gaussian Splat So cool to see this generative AI video to 3D workflow. Excited to see where it’s headed

I built an entire 3D editor this past weekend with -- using natural language 🤯 Powered by React, Three.js, and the Rapier physics engine. I believe AI will soon enable us to create the tools we need the moment we think of them. Thread 👇

Thursday night vibe coding with bolt.new (via Claude 3.7 Sonnet) Rapier + three.js 👀 debug mode

The future of the web looks different. Here is another WebAR experiment. Look at those details 👀 #AugmentedReality

Here’s how to create this cool 3D scene from a single image! 📸 Midjourney (isometric image generation) Trellis (Image to 3D Gaussian Splat) Browser Lab (3D Editor Splat Import)

Experimenting with image-to-world: creating consistent 3D environments from a single photo. As someone who studied architecture, this feels like a glimpse into the future of spatial creation and I’m excited to see where World Labs takes it.

Finally got my Gaussian Splat picture up and running in Augmented Reality—all via the web This is how I want to capture places + memories 🖼️ Where should I hang it up?

Face tracking + 3D model morph targets Built with Bolt Rendered Using Three.js Powered by MediaPipe Try the demo here: Bolt's new mascot maybe 😅 clone the project -&gt;

Claude 3.7 Sonnet is seriously impressive It goes beyond basic logic, capturing subtle nuances. Previous models for me was just about getting 3D experiences running, but 3.7 adds polished details—particle trails, collision visuals, and flawless physics #threejs

Morning stroll into a World Labs portal. I picture a future where you describe your environment and it instantly materializes around you.

Videos

Watch Anya Live

three.js is way more fun outside of the computer screen. Built w/ sol 5.6, world labs and webar

Testing sol 5.6 tonight. Built this using 8thWall webAR + sparkjs (open source) with a world labs gaussian splat generation of new interior design of my living room

I’m excited for the future of interfaces tools like this open up new ways to explore interactions pretext, three.js, world labs

almost at the point where we can just speak an experience into existence. Fable is amazing. But for iterating design ideas I think it's still a bit slow, went back to GPT 5.5 to finish building this. Environment generated with World Labs. full multiplayer if you want to try↓

First weekend building with Fable (it also helped put together this video) Open-sourced RC car raycast controller built with three.js + cannon. It includes mobile controls + Gamepad API support. It's also been a lot of fun implementing it with 3D Gaussian Splatting. Test it out!

20 million Gaussian splat of SF running all on a mobile device in WebAR. It’s really fun to move the phone around to zoom into different streets. Crazy to see the amount of detail in this scan Threejs + 8th Wall (now open source) + sparkjs

Late night experiment. I built a demo that generates 3D environments from images into 3DGS, then uses them as a spatial reference for directing real-time AR camera movements. The capture is then run through Seedance 2.0 for the final output. all running on the web via three.js↓

Really cool we’re at the point where you can build custom, personalized tools for your own niche 3D workflows. Built this with GPT-5.5, Spark, and Marble yesterday to get better precision + control for creating collider meshes for 3DGS experiences. Live:

Really cool seeing this on the quest in mixed reality. I put together a quick demo using WebXR (Three.js), Spark (LoD), and Danny’s raspberry Gaussian splat capture.

Finally got my game boy stylized portal running on the quest3 🕹️👀 I think I’ll stay in here for a while.

Why not use the real-world as a game level? This is a real-time augmented reality prototype using a physics based character controller, all running on the web 👀

Experimenting with environment styles in my off-axis projection demo. These are Gaussian splats rendered in the browser, switching via keyboard. -&gt; Blender basic layout -&gt; World Labs (chisel) -&gt; three.js / Spark 2.0 -&gt; Mediapipe (face-tracking)

I shrunk myself down to action figure size and can now interact with and explore the tiny world on my living room coffee table. Wait until 7 seconds in 👀🛋️

40m Coit Tower Gaussian splat in my living room. Built with GPT-5.5 + three.js (Spark 2.0 LoD). Running fully on-device via quest 3 If we could just get WebXR passthrough on Vision Pro too…

Persistent world models on the web. No 60-second time limit. World Labs × SparkJS × Three.js × Rapier 🌎

having fun bringing my ChatGPT Images 2.0 to life "A 360 image of a golden state warriors themed spaceship interior" then used Marble, Spark and Three.js to turn it into a persistent, interactive world I can walk around in. With some added DoF and splat particle effects

Pipeline: → Image (Midjourney) → Gaussian Splat (World Labs) → Web (SparkJS / Three.js) → Mixed Reality (Quest 3)

Off-axis projection experiment no. 2 mediapipe for face tracking, sparkjs for gaussian splat rendering via threejs

gaussian splat augmented reality portal 🚪

Testing off-axis projection demo. Basic scene layout in Blender glb -> detailed splat via World Labs Three.js for engine MediaPipe for face tracking Next step is to add a character you can move around in the environment

Visualizing my re-designed living room in 3D Nano banana -> World Labs -> WebAR (threejs) Each of these gaussian splats are only 1.5 mb in size (.spz file type)

Been experimenting with a similar technique lately Midjourney —> Gaussian Splat So cool to see this generative AI video to 3D workflow. Excited to see where it’s headed

Face tracking + 3D model morph targets Built with Bolt Rendered Using Three.js Powered by MediaPipe Try the demo here: Bolt's new mascot maybe 😅 clone the project ->

Experimenting with environment styles in my off-axis projection demo. These are Gaussian splats rendered in the browser, switching via keyboard. -> Blender basic layout -> World Labs (chisel) -> three.js / Spark 2.0 -> Mediapipe (face-tracking)