Theme
AI Visuals
TRELLIS.2
TRELLIS.2 is a Microsoft 3D generation model for high-fidelity image-to-3D asset creation, using O-Voxel structured latents, PBR materials, pretrained weights, inference code, and training tools.
The official repository presents TRELLIS.2 as a 4B-parameter image-to-3D system for generating textured 3D assets with complex topology, sharp features, and physically based rendering materials. Use this as a first read, not a recommendation. Open the original project before trusting details like terms, limits, privacy, cost, setup, or safety.
What it is
Image-to-3D generation model
TRELLIS.2 is positioned as a large 3D generative model for turning images into textured 3D assets, with code paths for inference, texture generation, training, and exported GLB assets.
Why it stands out
O-Voxel and PBR material focus
Microsoft's O-Voxel representation is designed to handle complex topology, open surfaces, non-manifold geometry, internal structures, and material attributes such as roughness, metallic, opacity, and base color.
Availability
Public repo with weights and demos
The repository includes setup instructions, example scripts, web demo files, Hugging Face pretrained-weight links, data-preparation guidance, and training code for readers who want to inspect the workflow.
Why it matters
What makes it useful
TRELLIS.2 combines Microsoft's O-Voxel representation with PBR material fields and GLB export, giving image-to-3D users a path from generation to a textured asset they can inspect in a wider 3D workflow.
What to know
Where it fits
Use it when an image-to-3D test needs textured geometry and PBR material fields that can continue into a GLB-based workflow. That reach comes with a technical Linux/CUDA setup, substantial GPU memory, and the need to check whether each generated asset is suitable for its intended pipeline.
Notable points
What stands out
The release pairs a 4B image-to-3D model and O-Voxel structured latents with PBR material modeling and GLB export. Pretrained checkpoints, inference examples, and full training code support both trying the model and examining how the workflow is built.
Before using
What to review
The Linux, CUDA, Conda, PyTorch, and dependency setup described in the official repository.
Hardware expectations, including the repository note that an NVIDIA GPU with at least 24GB of memory is needed for the tested setup.
How the model's image-to-3D, texture generation, GLB export, and training paths match the reader's intended workflow.
Whether the input image and generated asset can be used for the intended purpose, plus the current code and model terms at the official sources.
Reader fit
Who may find it relevant
Readers tracking 3D generation models, spatial AI, and image-to-3D asset workflows.
Builders exploring game assets, world-building, PBR materials, or 3D pipeline experiments.
Less relevant for readers focused mainly on text chatbots, coding agents, or lightweight local utilities.
Editorial note
Why LifeHubber lists it
TRELLIS.2 is worth considering when PBR materials and GLB export matter after image-to-3D generation. Readers still need to weigh that workflow fit against the 24GB tested-hardware note, setup effort, source-image rights, and the quality of the resulting asset for the job.
Source links
Source materials
Reader note
Before relying on this entry
LifeHubber lists entries to help readers inspect AI projects, not to endorse them or prove they are safe, suitable, accurate, maintained, or right for a specific use. We do not verify every entry in depth. Before relying on anything listed, review the original materials, terms, privacy practices, limits, and risks that matter for your situation.
More in AI Models
Keep browsing this category
Explore more AI model resources.
Gemma 4
google/gemma-4
A Google DeepMind Gemma 4 model family collection with public checkpoints including Gemma 4 12B, a dense multimodal model Google describes around local agentic workflows, native audio input, and encoder-free vision/audio handling.
Hy4 preview
tencent/Hy4-preview
Tencent Hy Team's preview-stage 770B-total, 49B-active Mixture-of-Experts language model for coding, document and analysis work, game development, research, tool use, and long-context tasks, with a 1M-token context window, public BF16 and FP8 weights, and dedicated vLLM or SGLang deployment paths.
Isaac GR00T N1.7
nvidia/gr00t-n17
An NVIDIA Isaac GR00T N1.7 vision-language-action model family for humanoid and generalist robot skills, with a 3B model, post-trained variants, GitHub code, inference and fine-tuning notes, LeRobot-format workflow support, and official robotics developer materials.
For project maintainers
Listed here? You can use the badge.
If you maintain a project with a current LifeHubber listing, you may add the optional “Listed on LifeHubber AI Resources” badge to its README, docs, or website. No introduction or permission request is needed.
