TRELLIS

What it does

Demo

The repository provides a Gradio web demo that users can run locally after installing its demo dependencies.checked 7 Oct 2001

Dependencies

Installation requires CUDA for compiling some submodules and Python 3.8 or higher, with Conda recommended for dependency management.checked 7 Oct 2001

Editing

It can generate variants of an asset and manipulate targeted local regions using text or image prompts.checked 7 Oct 2001

Exports

The usage example exports textured meshes as GLB and 3D Gaussians as PLY files.checked 7 Oct 2001

Formats

The example exports textured meshes as GLB files and 3D Gaussian representations as PLY files.checked 7 Oct 2001

Hardware

The code requires an NVIDIA GPU with at least 16 GB of memory; the repository says it has been verified on A100 and A6000 GPUs.checked 7 Oct 2001

Hardware requirement

The repository says an NVIDIA GPU with at least 16 GB of memory is necessary.checked 7 Oct 2001

License

TRELLIS models and most code use the MIT License, while some submodules have separate licenses.checked 7 Oct 2001

License and use

The project page says its materials are for academic and research purposes and are not intended for commercial use; the repository says the models and most code use the MIT License, with some submodules under different licenses.checked 7 Oct 2001

Model scale

The project provides pretrained models with up to 2 billion parameters, trained on a dataset of 500,000 3D assets.checked 7 Oct 2001

Model sizes

The project describes models with up to 2 billion parameters trained on a dataset of 500,000 3D objects.checked 7 Oct 2001

Model variants

The repository lists image-to-3D and text-to-3D pretrained models ranging from 342 million to 2 billion parameters.checked 7 Oct 2001

Operating system

The code is tested on Linux, and the repository describes Windows setup as not fully tested.checked 7 Oct 2001

Operating systems

The code is tested on Linux; Windows setup is described as not fully tested.checked 7 Oct 2001

Outputs

The model can produce Radiance Fields, 3D Gaussians, and meshes.checked 7 Oct 2001

Purpose

TRELLIS is a research model that generates 3D assets from text or image prompts.checked 7 Oct 2001

Quality

The project says its models generate detailed geometry and texture, while noting that photorealistic real-world object generation is limited.checked 7 Oct 2001

Representations

It can produce radiance fields, 3D Gaussians, and meshes from a shared Structured Latent representation.checked 7 Oct 2001

Research limits

The project page says the model is strongest at artistic-style assets and has limited ability to generate photorealistic real-world objects.checked 7 Oct 2001

Security reporting

The project directs vulnerability reports to the Microsoft Security Response Center rather than public GitHub issues.checked 7 Oct 2001

Support

The repository uses GitHub Issues for bug reports and feature requests, and says support is limited to the listed resources.checked 7 Oct 2001

Text-generation caveat

The repository recommends generating an image first and then using the image-conditioned model because text-conditioned models are less creative and detailed due to data limitations.checked 7 Oct 2001

Web demo

The repository provides a Gradio web demo that users can install and run locally.checked 7 Oct 2001