I've open sourced this project! - use voice commands to change interaction mode (drag, rotate, scale, animate) - use hand gestures to control the 3D model - drag/drop to import other models (only GLTF format supported rn) created using Three.js, Rosebud AI, mediapipe computer vision, web speech API, and... Quaternius 3D models 🔗 github repo belowshow more

github repo: live demo:

Here's the open source repo I promised you! @JeremyNguyenPhD @bilawalsidhu @lightfi_crypto @connor_online @mjshunya @johngoad @MarkDKBerry @lalopenguin @alightinastorm @csanz @josunlouise @turbotardo @rilso_y @jorgenicolau_ar @bingpong69 It would be much appreciated if you could support the original post:

@threejs @Rosebud_AI Wow!! Thanks for making this open source!

@threejs @Rosebud_AI feel free to hack some cool stuff with it. would love to see what people come up with :)

@threejs @Rosebud_AI Works really smooth! Nice one

@threejs @Rosebud_AI thank you Majid 🙇‍♂️ I'll continue to explore this! In my head it feels like a neat way for 3D designers to showcase their work while they're on a video call

@threejs @Rosebud_AI That's cool man!

@threejs @Rosebud_AI Imagine if we could create generative 3D characters and videos on the fly and direct them in a scene this way 😲

@threejs @Rosebud_AI Make it a tamagoochi style - add a tts on top and make characters alive.

@threejs @Rosebud_AI That would be so fun, I’ll try it thank you :)