Show HN: Run TRELLIS.2 Image-to-3D generation natively on Apple Silicon

that makes so much sense...I am exploring if I can find someone who has done this well...If not I'll try to do it myself.

Hey, thanks for sharing this. I'm sure TRELLIS.2 definitely has room to improve, especially on texturing.

From what I've seen personally, and community benchmarks, it does fair on geometry and visual fidelity among open-source options, but I agree it's not perfect for every use case.

Meshy is solid, I used it to print my girlfriend a mini 3d model of her on her birthday last year!

Though worth noting it's a paid service, and free tier has usage limitations while TRELLIS.2 is MIT licensed with unlimited local generation. Different tradeoffs for different workflows. Hopefully the open-source side keeps improving.

Meshy is indeed great but I am terminally put off by their alltogether terrible, sleazy, gamified, opaque web UI. It's like aliexpress and a lootbox game had a baby that's into mesh generation. Ugh.

[dead]

They’re completely different projects. ML Sharp is designed to create a 3D Gaussian representation of a depicted scene and output a splat file. Trellis generates model files (GLB I believe) for use with 3D modeling applications.

You're right, thanks for flagging this, let me run something and push images

added! will add more, maybe even a GIF

The model needed about 15GB at peak during generation - the 4B model loads multiple sub-models (1.3B each for shape and texture flow). 8GB won't be enough, but both 24GB and 32GB both should be fine.

[dead]

IMO TRELLIS.2 is slightly different case from the HF models scenario. It depends on five compiled CUDA-only extensions -- flex_gemm for sparse convolution, flash_attn, o_voxel for CUDA hashmap ops, cumesh for mesh processing, and nvdiffrast for differentiable rasterization. These aren't PyTorch ops that fall back to MPS -- they're custom C++/CUDA kernels. The upstream setup.sh literally exits with "No supported GPU found" if nvidia-smi isn't present. The only reason I picked this up because I thought it was cool and no one was working on this open issue for Silicon back then (github.com/microsoft/TRELLIS.2/issues/74) requesting non-CUDA support.

Are you saying the original one worked with MPS? Or are you just saying it was always theoretically possible to build what OP posted?

It’s always been possible, but it’s not possible because there’s no backend, and no one wants to it to be possible because everyone needs it 10x the speed of running on a Mac? I’m missing something, I think.

rad. how long does output take? trellis is a fun model.

thanks!

Sunday night, and its kinda cool idk man

I mean I can see that it's niche. Did not expect so many upvotes, but ig it's less niche than I tought

If you're not working with 3D on Apple Silicon this isn't relevant to you. For the subset of people who are, running this 4B parameter 3D generation model locally on a Mac was previously blocked by hard CUDA dependencies with no workaround.

Good question.