Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

TRELLIS.2: state-of-the-art large 3D generative model (4B)

github.com

Post reply on HN
Print view View original

11–18 of 18 posts

Re: TRELLIS.2: state-of-the-art large 3D generative model (4B)

#11

Post by summarity »

dvh wrote: post #10

Where they get training data from?

> All our model, code, and dataset will be publicly released to facilitate reproduction and further research.

Will take some time to publish. The TRELLIS 1 dataset is public here: https://github.com/microsoft/TRELLIS/blob/main/DATASET.md

Re: TRELLIS.2: state-of-the-art large 3D generative model (4B)

#13

Post by Geee »

OldMatey wrote: post #8

State of the art for Open Source. This is a nice improvement, but far out I cannot wait for a Sparc3D equivalent for local use. Its a step change in quality. I really hope Hunyuan3D-3 is the one to level up to that quality now

To me it seems Trellis 2 has higher quality and it also generates PBR materials and textures.

Re: TRELLIS.2: state-of-the-art large 3D generative model (4B)

#15

Post by shen »

visioninmyblood wrote: post #5
NotGMan wrote: post #4

Needs 24GB gpu to run.

you can chat with vlm.run to generate these assets from image generation without needing a gpu. Modi: https://chat.vlm.run/c/bdbaf1dc-b3c2-4b8a-ad17-6e26d87475fd Musk: https://chat.vlm.run/c/894f44ce-c366-4c93-b348-de6eebfb9f03 Ronaldo: https://chat.vlm.run/c/db5eff27-8c52-4e0b-8e4e-157df6bef278 Gomez: https://chat.vlm.run/c/02b92f23-a6fd-4380-b7a9-52ae7463c9c1 Jackie chan: https://chat.vlm.run/c/62ca5502-2066-4d5f-b…

Got a good laugh out of these, thanks.

Re: TRELLIS.2: state-of-the-art large 3D generative model (4B)

#16

Post by momojo »

I'm surprised at the lukewarm reception. Admittedly I don't follow the image-to-3D space as much, but last time I checked in, the gloopy fuzzy outputs did not impress me.

I want to highlight what I believe is the coolest innovation: their novel O-Voxel data structure. I'm still trying to wrap my head around how they figured out the conversion from voxel-space to mesh-space. Those two worlds don't work well together.

A 2D analogy is that they figured out an efficient, bidirectional, one-shot method of converting PNG's into SVG's, without iteration. Crazy.

Re: TRELLIS.2: state-of-the-art large 3D generative model (4B)

#17

Post by visioninmyblood »

shen wrote: post #15
visioninmyblood wrote: post #5

Earlier quoted context omitted.

you can chat with vlm.run to generate these assets from image generation without needing a gpu. Modi: https://chat.vlm.run/c/bdbaf1dc-b3c2-4b8a-ad17-6e26d87475fd Musk: https://chat.vlm.run/c/894f44ce-c366-4c93-b348-de6eebfb9f03 Ronaldo: https://chat.vlm.run/c/db5eff27-8c52-4e0b-8e4e-157df6bef278 Gomez: https://chat.vlm.run/c/02b92f23-a6fd-4380-b7a9-52ae7463c9c1 Jackie chan: https://chat.vlm.run/c/62ca5502-2066-4d5f-b…

Got a good laugh out of these, thanks.

was fun generating the as well
Post reply on HN