Microsoft open-sourced a 4B model that turns any image into a production-ready 3D asset in 3 seconds. It’s called TRELLIS.2, a fully textured, physically accurate 3D models with PBR textures out of the box. → Full PBR (base color, roughness, metallic, opacity) → Handles hair, cloth, glass, non-manifold geometry... → Exports .glb ready for Unity/Unreal/Blender → Runs locally, ships in 3 seconds It's not a demo or a research preview. The full training codebase is public. You can fine-tune it on your own asset library and get a model that generates in your studio's exact style. 100% Open Sourceshow more

Repo:

i have seen a few posts similar to this, and i decided to play around with all the AI tools to see how they can't make actual cad models. Not one has produced anything close to an object that you could actually use. Making a AI video like this isn't the same thing!CADcanIIan

topology is probably a mess

that came out 7 months ago

This is a bullshit model that requires another GATED model DinoV3 that you need to get META to approve. Open my ass.

*cries in

Tell me you haven’t used it without tell me

Does it work for 3D printing?

That was released a while ago

TRELLIS.2 suena prometedor pero 3 segundos para un asset 3D con PBR completo es un salto enorme. Me pregunto qué tan bien escala con geometría compleja o si solo funciona para objetos simples.

The gaming industry will take a hit with this one. More and more people are testing AI’s on abilities to clone games. If this becomes the standard, I wouldn’t know the difference between hand made games and AI made games. Both will be amazing to play though.

This is Epic. Thanks @Microsoft Trellis is the best png to glb 2d to 3d model transformer and will be the rise to generative 3d models from image generation with #threejs and #aiuiuxjs apps and sims.

open source is doing the heavy lifting

hey cool thanks for sharing a 6 month old repo this is the equivalent of 2,000 human years in the world of AI

@threejs It is good before you see topology :)

waiting on these things to get animated. I am good with tripo3d for now and meshyAI

Prerequisites System: The code is currently tested only on Linux. Hardware: An NVIDIA GPU with at least 24GB of memory is necessary. The code has been verified on NVIDIA A100 and H100 GPUs. Let me just grab my $8k - 30k GPU quick.

Has anyone tried running this locally yet? Wondering how much VRAM it needs.

@Spectromachina thought of you as soon as I saw this

Production ready? Lmao. Guess china can just take a picture of a raptor engine and spacex edge is gone

"Runs locally, fully open training codebase" is the detail worth highlighting more than the speed — no cloud dependency, no data leaving your machine for asset generation. That's a meaningfully different trust model than most generative tools shipping right now

This can be use directly in Modly 👀

@SpaceXAI this is exactly the asset extraction feature I was suggesting for @grok imagine images and videos. Basically you begin with a prompt to produce an image and refine it. Each image is a sample run. The right image is then a reference point for an animation scene. The extrusion of the 2D asset to a timeline in motion produces extrapolated logical 3D geometry. That scene/video acts as the basis for multiple 3D assets which can be selected extracted and saved as .STL .obj .NC .gcode .ply .f3z .rvt and .dxf for example. (Autodesk, Gaussian splats, 3D printer, 360 fusion etc.) The combined outputs would be physicalization and phygital or virtualization products, such a chair, scale figure, or partially/wholly complete hypercar, scaling detail with iterative models. I'm surprised 4B already gets close.

goodbye to yet another profession and market

this gets posted like every two weeks

Can it do anatomy?

@loktar00 may be helpful with your characters.

fine tuning on your own assets is the real flex

Necessary. Now we can divide logic and tasks up to engage multiple resins types and tools completing a synchronized project with a data centre, functioning as a digital brain running a gyroscopic masterpiece of biomimicry. Modeled after a tree, an octopus, a spider…or fungi

In then meantime they also shipped Windows 11 and Cortana.

Image-to-3D is a reasoning problem, not pixel generation - the model infers geometry it never sees. Shipping it at 4B open-weights is the real story: it drops into a local creative pipeline with no cloud round-trip. #GenAI #AITools @Microsoft

Open-weights 4B models running locally on consumer GPUs disrupt traditional asset pipelines. Sub-second inference with PBR textures eliminates the 0-00 per-asset API cost from proprietary cloudservices. How is VRAM consumption holding up during batch processing?

Ah older news

Can’t wait for @machineviolence to go 3d 😁

pretty cool