Show HN: Trellis 3D AI – Turn any image into 3D assets using AI

[yangxiaobo]

Hi HN!

I've built TRELLIS 3D AI, an open tool that converts 2D images into professional 3D assets using advanced AI technology.

Technical Implementation: - Browser-based processing using WebGL - Structured LATents (SLAT) for maintaining geometric integrity - Dual output pipeline generating both GLB and 3D Gaussian formats - Real-time 3D preview using Three.js - Optimized for processing images up to 2048x2048px

The core technology combines: - Pretrained vision encoders for image understanding - Rectified flow transformers for 3D geometry generation - Advanced neural networks for texture mapping

Current Specs: - Processing time: ~30s per image - Output formats: GLB + 3D Gaussian - Zero external dependencies - Runs entirely client-side

Currently it's using Hugging Face for processing, and I plan to implement API integration in the future to enable more advanced features.

Live demo: https://trellis3d.co/

Would love your feedback and suggestions for improvements.

[maalber]

This is actually really cool. First tried with one of the example images which of course worked really well. I then tried with a couple of images I had lying around on my own PC which also worked surprisingly well! Nice work. A couple of questions: I see that the 3D preview is a video playback, have you considered making it an actual 3D viewport?

Can you provide some additional insights into your process? Did you train the generation models yourself? And if so can you talk a bit about the process?

[gexaha]

From what I understand, you are not the author of the original paper, and you just took and copied everything from the original authors, even the website and the gradio demo?

[lizzas]

That is damn good!