Gábor Pribék's banner

Gábor Pribék

@gaborpribek • 2,087 subscribers

Head of Product Design at @Splinetool, @Omma_ai, Past @Shapr3d, @Prezi.

Shorts

2M+ voxels reconstructing real-world terrain and rivers. Real-time, inside a landing page. Made with Omma AI uses Three.js.

2M+ voxels reconstructing real-world terrain and rivers. Real-time, inside a landing page. Made with Omma AI uses Three.js.

65,195 Aufrufe

Exploring !Boring stickers! in 3D, made with Omma AI.

Exploring !Boring stickers! in 3D, made with Omma AI.

276,143 Aufrufe

What if anatomy explorers felt alive? This 3D dog, including the skeleton, organs and rig, was generated with ai and reacts to the cursor in real time with head tracking and tail movement. - Used GPT Images 2 for consistency - Omma AI for 3D generation and code using Three.js Lmk if you’d like to try it!

What if anatomy explorers felt alive? This 3D dog, including the skeleton, organs and rig, was generated with ai and reacts to the cursor in real time with head tracking and tail movement. - Used GPT Images 2 for consistency - Omma AI for 3D generation and code using Three.js Lmk if you’d like to try it!

204,419 Aufrufe

HTML enters 3D! Or vice versa? With the new HTML in Canvas by WICG, we can finally put native DOM elements directly into WebGL/WebGPU scenes. It is experimental for now, but the possibilities for 3D interfaces and special effects are huge. This demo was built using Three.js and Omma AI (tool by Spline ) It’s a fun new way to explore what the web can do! Are you interested in seeing the demo?

HTML enters 3D! Or vice versa? With the new HTML in Canvas by WICG, we can finally put native DOM elements directly into WebGL/WebGPU scenes. It is experimental for now, but the possibilities for 3D interfaces and special effects are huge. This demo was built using Three.js and Omma AI (tool by Spline ) It’s a fun new way to explore what the web can do! Are you interested in seeing the demo?

176,065 Aufrufe

Depth Anything V2 is a total beast for real-time 3D. Built a website that hits 30fps+ depth reconstructions from a single camera feed, extruding 12k voxels via WebGPU. Pure ML running local Vision Transformers with Three.js and zero backend lag. Lmk in the comments if you want a copy! 🙌 Experience and music made with AI in Omma AI (tool by Spline).

Depth Anything V2 is a total beast for real-time 3D. Built a website that hits 30fps+ depth reconstructions from a single camera feed, extruding 12k voxels via WebGPU. Pure ML running local Vision Transformers with Three.js and zero backend lag. Lmk in the comments if you want a copy! 🙌 Experience and music made with AI in Omma AI (tool by Spline).

142,027 Aufrufe

Played around with generating the internal anatomy of a creature (skeletons and organs). I used GPT Images 2 to keep the creature anatomy consistent, while the code, interactions and 3D models were generated with Omma AI and uses Three.js.

Played around with generating the internal anatomy of a creature (skeletons and organs). I used GPT Images 2 to keep the creature anatomy consistent, while the code, interactions and 3D models were generated with Omma AI and uses Three.js.

75,774 Aufrufe

Physics via OS window shake is so much fun! Original scene by mrdoob and physics exploration by Gonçalo Teixeira made in Omma

Physics via OS window shake is so much fun! Original scene by mrdoob and physics exploration by Gonçalo Teixeira made in Omma

26,977 Aufrufe

I used the GPT Image 2 "360 equirectangular [subject: cats]" trick and turned them into 360 immersive videos! Videos and interactive 3D experience using Three.js generated with Omma AI (tool by Spline ) Planning to share the workflow and experience on Omma community, lmk if you are interested!

I used the GPT Image 2 "360 equirectangular [subject: cats]" trick and turned them into 360 immersive videos! Videos and interactive 3D experience using Three.js generated with Omma AI (tool by Spline ) Planning to share the workflow and experience on Omma community, lmk if you are interested!

23,527 Aufrufe

Just built a 3D Strava/Apple Health fitness visualizer in Omma AI (by Spline) that turns .gpx files into 3D terrain with live metrics. Drag, drop, and watch your run come to life in real-time. Lmk if you want to remix and test with your own data!

Just built a 3D Strava/Apple Health fitness visualizer in Omma AI (by Spline) that turns .gpx files into 3D terrain with live metrics. Drag, drop, and watch your run come to life in real-time. Lmk if you want to remix and test with your own data!

19,896 Aufrufe

Vibe-coded a "Ponku" sticker experience to mirror how Apple is blending iPhone hardware with Korea Emojis. 🌈📱 3D iPhone by Ranguel on Sketchfab. Built with AI in Omma by Spline. Lmk in the comments if you would like to grab a copy of the experience!

Vibe-coded a "Ponku" sticker experience to mirror how Apple is blending iPhone hardware with Korea Emojis. 🌈📱 3D iPhone by Ranguel on Sketchfab. Built with AI in Omma by Spline. Lmk in the comments if you would like to grab a copy of the experience!

17,196 Aufrufe

AI meets 3D anatomy? I made a real-time interactive 3D cat that reacts to your cursor with head tracking and tail movement. The skeleton, organs and rig were generated with AI using Omma and rendered with Three.js. Curious if you would actually use something like this.

AI meets 3D anatomy? I made a real-time interactive 3D cat that reacts to your cursor with head tracking and tail movement. The skeleton, organs and rig were generated with AI using Omma and rendered with Three.js. Curious if you would actually use something like this.

11,392 Aufrufe

GPT Image 2.0 + Generated Normal Maps = Dynamic Lighting and Shadows for UI. 🤯 The workflow for building high-fidelity skeuomorphic UI concepts with AI + Three.js just got a lot easier. Interactive experience, sound fx, and normals all generated with Omma AI (tool by Spline). 3D iPhone by Ranguel on Sketchfab. Happy to share the remix link if you would like to poke around, lmk!

GPT Image 2.0 + Generated Normal Maps = Dynamic Lighting and Shadows for UI. 🤯 The workflow for building high-fidelity skeuomorphic UI concepts with AI + Three.js just got a lot easier. Interactive experience, sound fx, and normals all generated with Omma AI (tool by Spline). 3D iPhone by Ranguel on Sketchfab. Happy to share the remix link if you would like to poke around, lmk!

12,290 Aufrufe

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

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?

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?

48,030 Aufrufe • vor 2 Monaten

Move AI agents into your sketchbook!? It watches you draw in real-time to brainstorm and generate SVGs. To get this running entirely in a single client-side HTML file, I had to build: - My own "DeskView" un-distort from the iPad's wide angle camera (via WebGL homography, DeskView is not available on iPads natively) - WebGPU shaders for the audio-reactive holographic edge glow - WebSocket streaming for the voice/vision loop via Google Gemini AI Live API Built with natural language in Omma AI Would you like to try?

Move AI agents into your sketchbook!? It watches you draw in real-time to brainstorm and generate SVGs. To get this running entirely in a single client-side HTML file, I had to build: - My own "DeskView" un-distort from the iPad's wide angle camera (via WebGL homography, DeskView is not available on iPads natively) - WebGPU shaders for the audio-reactive holographic edge glow - WebSocket streaming for the voice/vision loop via Google Gemini AI Live API Built with natural language in Omma AI Would you like to try?

16,050 Aufrufe • vor 2 Monaten

Keine weiteren Inhalte verfügbar