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

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…

these are garbage compared to what's shown in the posting.

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

#7

Post by summarity » Thu, Dec 18, 2025, 9:57 PM UTC

TRELLIS 1 had a massive impact on the research in this area, not least because it’s actually open (full dataset, training and inference). Research like SynCity or PhysX-3D (not the NVIDIA one) wouldn’t have been possible.

Excites for the follow ups for this new generation.

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

#8

Post by OldMatey » Thu, Dec 18, 2025, 10:06 PM UTC

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

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

#9

Post by nice_byte » Thu, Dec 18, 2025, 10:07 PM UTC

You can play with a demo here: https://huggingface.co/spaces/microsoft/TRELLIS.2 (requires a hugging face acct)

The results from arbitrary pictures are not nearly as good as what's shown in the posting. So either the demo is running a gimped version of the model or the examples are _very_ handpicked.

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

#10

Post by dvh » Thu, Dec 18, 2025, 10:11 PM UTC

Where they get training data from?