Loading video...

Video Failed to Load

Go Home

Today I'm presenting Omma Face Studio, a web-based MetaHuman editor with direct sync to your webcam. I developed it in Omma AI using Google's GNM engine: a complete 3D parametric human model, which I was able to adapt for Three.js.

parazar's profile picture

Joseph Azar

2,529 subscribers

48,339 views • 6 days ago •via X (Twitter)

ArtsScience & TechnologyGaming
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Wild what's possible now: I can ship a 3D experience prototype to a museum in a single afternoon. Everything coded and generated with Omma, leveraging AI to iterate fast. 3D models generated in Omma. Scene built on top of Three.js. Prompted for dissolving shaders + particle systems?
0:30

Wild what's possible now: I can ship a 3D experience prototype to a museum in a single afternoon. Everything coded and generated with Omma, leveraging AI to iterate fast. 3D models generated in Omma. Scene built on top of Three.js. Prompted for dissolving shaders + particle systems?

Joseph Azar

93,343 views • 2 months ago

Introducing Omma Studio, a full suite of AI tools to generate 3d, video/image, and audio with SOTA models. Everything made in Studio can integrate directly with your Omma's chat code projects to deploy/publish to the web. Content can be generated in parallel alongside your code generation in Omma, too. Studio -> Code -> Deploy
0:37

Introducing Omma Studio, a full suite of AI tools to generate 3d, video/image, and audio with SOTA models. Everything made in Studio can integrate directly with your Omma's chat code projects to deploy/publish to the web. Content can be generated in parallel alongside your code generation in Omma, too. Studio -> Code -> Deploy

Omma AI

22,584 views • 1 month ago

Still experimenting with hand tracking 🖐️ using a webcam and the dear Carlo. The 3D model was generated from a single image in Omma AI Studio, and I remixed an Octopus demo to take advantage of the physics simulation. Building with AI these days is so much fun. Music also generated from the Studio (Fan Art) #threeJS
0:58

Still experimenting with hand tracking 🖐️ using a webcam and the dear Carlo. The 3D model was generated from a single image in Omma AI Studio, and I remixed an Octopus demo to take advantage of the physics simulation. Building with AI these days is so much fun. Music also generated from the Studio (Fan Art) #threeJS

Joseph Azar

74,107 views • 1 month ago

I built a Domino editor, a full playground where you can draw your own course, edit curves, and add structures to knock down, bridges, and staircases. Thousands of dominoes can topple in a single chain reaction 🤯 The whole thing was created in Omma AI Studio. For the physics, I used the Box3D library with Three.js. Works incredibly well!!
1:20

I built a Domino editor, a full playground where you can draw your own course, edit curves, and add structures to knock down, bridges, and staircases. Thousands of dominoes can topple in a single chain reaction 🤯 The whole thing was created in Omma AI Studio. For the physics, I used the Box3D library with Three.js. Works incredibly well!!

Joseph Azar

20,235 views • 8 days ago

I've never prototyped this fast in my life! Fable 5 + Omma AI Studio is the perfect combo for building game prototypes with Three.js. Here's what I made today: a Forza Horizon-style racing game 'Omma Redline'. The 4x4 suspension is my favorite part: super responsive. I built two different biomes, and the tire tracks in the snow are just way too cool. Everything came out of Omma Studio: the car models, materials, textures, code, even the music. Still a work in progress, more polishing to come :)
1:04

I've never prototyped this fast in my life! Fable 5 + Omma AI Studio is the perfect combo for building game prototypes with Three.js. Here's what I made today: a Forza Horizon-style racing game 'Omma Redline'. The 4x4 suspension is my favorite part: super responsive. I built two different biomes, and the tire tracks in the snow are just way too cool. Everything came out of Omma Studio: the car models, materials, textures, code, even the music. Still a work in progress, more polishing to come :)

Joseph Azar

12,783 views • 17 days ago

Turn your playlist into a rhythm game. I built a fully procedural cartoon lowrider you control with a gamepad. Try to bounce, hop and lean in time with the music yourself. Turn on your audio 🔥 Built inside Omma AI with Three.js & Claude
0:57

Turn your playlist into a rhythm game. I built a fully procedural cartoon lowrider you control with a gamepad. Try to bounce, hop and lean in time with the music yourself. Turn on your audio 🔥 Built inside Omma AI with Three.js & Claude

Joseph Azar

20,087 views • 15 days ago

I prompted Omma to build a #threejs app with real dynamic lighting on a 3D mesh - generated from a single image, using Depth Anything v2 + Transformers from Hugging Face ⚡ Depth estimation in the browser 🫧 3D mesh from the depth map 💡 Dynamic lighting reacting to the geometry No manual code. Pure AI prompting. The future of 3D on the web feels wide open.
0:40

I prompted Omma to build a #threejs app with real dynamic lighting on a 3D mesh - generated from a single image, using Depth Anything v2 + Transformers from Hugging Face ⚡ Depth estimation in the browser 🫧 3D mesh from the depth map 💡 Dynamic lighting reacting to the geometry No manual code. Pure AI prompting. The future of 3D on the web feels wide open.

Joseph Azar

14,041 views • 2 months ago

Continuing to enhance my web-based 3D editor built entirely with natural language via powered by Three.js + React. You can now create a basic scene and transform it into a work of art using Stability AI’s Structure Model. Try it out yourself 👇
0:31

Continuing to enhance my web-based 3D editor built entirely with natural language via powered by Three.js + React. You can now create a basic scene and transform it into a work of art using Stability AI’s Structure Model. Try it out yourself 👇

Ian Curtis

65,302 views • 1 year ago

Tired of waiting for the "New Siri" so I built it myself. Combining Google Gemini AI Live with WebGPU for a 3D-aware "Visual Intelligence" prototype. - Three.js for Apple Intelligence glow shader. - Depth-Anything Local ML for real-time 3D scanning effect. - Gemini Live for Multimodal voice + vision. Built with Omma AI. Lmk if you would like to try or remix! Anyone here planning to go to WWDC26?
0:20

Tired of waiting for the "New Siri" so I built it myself. Combining Google Gemini AI Live with WebGPU for a 3D-aware "Visual Intelligence" prototype. - Three.js for Apple Intelligence glow shader. - Depth-Anything Local ML for real-time 3D scanning effect. - Gemini Live for Multimodal voice + vision. Built with Omma AI. Lmk if you would like to try or remix! Anyone here planning to go to WWDC26?

Gábor Pribék

48,030 views • 2 months ago

My wife and daughter told me about Crocs Jibbitz, so I built a 3D editor to place them naturally and pick your favorites before buying. Ready to integrate into an e-commerce service? Why not it's a prototype anyway, made possible thanks to Omma AI + #threeJS.
0:41

My wife and daughter told me about Crocs Jibbitz, so I built a 3D editor to place them naturally and pick your favorites before buying. Ready to integrate into an e-commerce service? Why not it's a prototype anyway, made possible thanks to Omma AI + #threeJS.

Joseph Azar

15,221 views • 23 days ago

AI 3D workflows for web are getting scary good. Here is a demo with a large splat background (+LoD), mesh character, spatial audio, VR support, and lighting. I was able to create it in a few hours (repo in reply). built with Three.js spark World Labs Audio on :)
1:03

AI 3D workflows for web are getting scary good. Here is a demo with a large splat background (+LoD), mesh character, spatial audio, VR support, and lighting. I was able to create it in a few hours (repo in reply). built with Three.js spark World Labs Audio on :)

martin_casado

82,439 views • 7 months ago

Took it further with Omma AI, (Spline ) now it works on video, and everything working in a Web Browser. Drop a video, Depth Anything v2 calculates the depth map frame by frame, and Three.js renders a fully lit 3D mesh in real time. Depth estimation on video in the browser +Automatic baking pass + Dynamic lighting reacting to the geometry #vibecoding #threejs #webgl
0:40

Took it further with Omma AI, (Spline ) now it works on video, and everything working in a Web Browser. Drop a video, Depth Anything v2 calculates the depth map frame by frame, and Three.js renders a fully lit 3D mesh in real time. Depth estimation on video in the browser +Automatic baking pass + Dynamic lighting reacting to the geometry #vibecoding #threejs #webgl

Joseph Azar

147,773 views • 2 months ago

Really proud of what I was able to achieve developing 3D cell nuclei with custom geometry shaders using Three.js for a cancer care platform, all built with Google Gemini 3 Pro AI 💜 Had to approach the project twice, but had a lot of fun doing it :) Live:
0:30

Really proud of what I was able to achieve developing 3D cell nuclei with custom geometry shaders using Three.js for a cancer care platform, all built with Google Gemini 3 Pro AI 💜 Had to approach the project twice, but had a lot of fun doing it :) Live:

The Bugged Dev

19,420 views • 6 months ago

omg.. I can't believe this.. this Unreal Engine AI plugin lets you generate 3D model in seconds with text prompt, and even chat with AI to optimise your scene.. A revolutionary AI tool for 3D creation. here's how to get started:
0:46

omg.. I can't believe this.. this Unreal Engine AI plugin lets you generate 3D model in seconds with text prompt, and even chat with AI to optimise your scene.. A revolutionary AI tool for 3D creation. here's how to get started:

el.cine

129,956 views • 1 year ago

OpenAI just released a new model to distinguish between AI/human written text to protect against ChatGPT. The classifier was trained on a pair of AI/human written dataset. However.. I was easily able to trick it by using GPT3 to rewrite the text. Demo:
0:32

OpenAI just released a new model to distinguish between AI/human written text to protect against ChatGPT. The classifier was trained on a pair of AI/human written dataset. However.. I was easily able to trick it by using GPT3 to rewrite the text. Demo:

Lior Alexander

195,429 views • 3 years ago

Excited to share a new vibe coded prototype: an interactive lesson on ants and their habitat, designed for elementary school students. AI allowed me to finalize this demo quickly. Some educational details still need review, but the main chambers of an anthill are all represented. Everything was made in Omma AI , a Spline product. What's inside: - 3D models created with Omma, all I needed was one image of the anthill's exterior and another of its cross-section to generate both 3D models - Clouds done with sprites - A custom shader mask to reveal the inside of the anthill This was a really fun one to work on!
0:43

Excited to share a new vibe coded prototype: an interactive lesson on ants and their habitat, designed for elementary school students. AI allowed me to finalize this demo quickly. Some educational details still need review, but the main chambers of an anthill are all represented. Everything was made in Omma AI , a Spline product. What's inside: - 3D models created with Omma, all I needed was one image of the anthill's exterior and another of its cross-section to generate both 3D models - Clouds done with sprites - A custom shader mask to reveal the inside of the anthill This was a really fun one to work on!

Joseph Azar

19,853 views • 2 months ago

Holy moly, I finally vibe coded a website I’ve always dreamt of building 🥹 Nah, it’s not a Blender model. Not even for 3D podium. It’s pure geometry built using Three.js with color maps (albedo), spring-based physics, a hybrid DOM, real-time planar reflections, and more. Completely vibe coded all using Gemini 3 Pro in Google AI Studio!! Live:
0:22

Holy moly, I finally vibe coded a website I’ve always dreamt of building 🥹 Nah, it’s not a Blender model. Not even for 3D podium. It’s pure geometry built using Three.js with color maps (albedo), spring-based physics, a hybrid DOM, real-time planar reflections, and more. Completely vibe coded all using Gemini 3 Pro in Google AI Studio!! Live:

The Bugged Dev

170,996 views • 5 months ago

asked Fable to improve my rendering of the hairy guy, this looks good enough! took just a few prompts in Omma AI to get it right, the hair material is just a cheap #tsl LambertNodeMaterial with some custom specular lighting model based on the Kajiya-Kay lobes
0:39

asked Fable to improve my rendering of the hairy guy, this looks good enough! took just a few prompts in Omma AI to get it right, the hair material is just a cheap #tsl LambertNodeMaterial with some custom specular lighting model based on the Kajiya-Kay lobes

Marco Fugaro

39,089 views • 17 days ago

MTMB RESET I'm experimenting with a new facegraphic system for RESET. I had the idea to make the face graphics "animated" (idle). It's using planes in a 3D space. My wife is modifying the engine to import bones for animations. This would make it easy to animate + space saving.
0:52

MTMB RESET I'm experimenting with a new facegraphic system for RESET. I had the idea to make the face graphics "animated" (idle). It's using planes in a 3D space. My wife is modifying the engine to import bones for animations. This would make it easy to animate + space saving.

CorpseSyndrome

25,321 views • 2 years ago

After 20 years I can finally build this interface :D!!☝️☝️ How it works: human (me) moves fingers->webcam records fingers->AI (Google's MediaPipe) recognizes fingers and gestures->human interacts with web elements. Link to the code in the next tweet:
0:44

After 20 years I can finally build this interface :D!!☝️☝️ How it works: human (me) moves fingers->webcam records fingers->AI (Google's MediaPipe) recognizes fingers and gestures->human interacts with web elements. Link to the code in the next tweet:

Nacho Martín

103,189 views • 3 years ago