{"name":"TRELLIS: Structured 3D Latents for Scalable and Versatile 3D Generation","description":"TRELLIS is the official repository for a CVPR'25 Spotlight paper on \"Structured 3D Latents for Scalable and Versatile 3D Generation.\" This Microsoft project introduces a powerful model for generating high-quality 3D assets from text or image prompts. It supports diverse output formats like Radiance Fields, 3D Gaussians, and meshes, offering flexible editing capabilities.","github":"https://github.com/microsoft/TRELLIS","url":"https://osrepos.com/repo/microsoft-trellis","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/microsoft-trellis","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/microsoft-trellis.md","json":"https://osrepos.com/repo/microsoft-trellis.json","topics":["3d","3d-aigc","3d-generation","image-to-3d","text-to-3d","Python","AI","Machine Learning"],"keywords":["3d","3d-aigc","3d-generation","image-to-3d","text-to-3d","Python","AI","Machine Learning"],"stars":null,"summary":"TRELLIS is the official repository for a CVPR'25 Spotlight paper on \"Structured 3D Latents for Scalable and Versatile 3D Generation.\" This Microsoft project introduces a powerful model for generating high-quality 3D assets from text or image prompts. It supports diverse output formats like Radiance Fields, 3D Gaussians, and meshes, offering flexible editing capabilities.","content":"## Introduction\n\nTRELLIS is the official repository for the paper \"Structured 3D Latents for Scalable and Versatile 3D Generation,\" recognized as a CVPR'25 Spotlight. Developed by Microsoft, TRELLIS introduces a powerful 3D asset generation model that can create high-quality 3D assets from both text and image prompts. Its core innovation lies in a unified Structured LATent (SLAT) representation, enabling versatile decoding into various 3D formats, including Radiance Fields, 3D Gaussians, and meshes. This project offers large-scale pre-trained models and advanced capabilities for flexible 3D editing.\n\n## Installation\n\nTo get started with TRELLIS, follow these steps:\n\n### Prerequisites\n-   **System**: Linux is currently tested.\n-   **Hardware**: An NVIDIA GPU with at least 16GB of memory (A100, A6000 recommended).\n-   **Software**: CUDA Toolkit (11.8 or 12.2), Conda for dependency management, Python 3.8 or higher.\n\n### Installation Steps\n1.  **Clone the repository**:\n    sh\n    git clone --recurse-submodules https://github.com/microsoft/TRELLIS.git\n    cd TRELLIS\n    \n\n2.  **Install dependencies**:\n    This command creates a new conda environment named `trellis` and installs all necessary dependencies. Refer to `. ./setup.sh --help` for detailed options and flags.\n    sh\n    . ./setup.sh --new-env --basic --xformers --flash-attn --diffoctreerast --spconv --mipgaussian --kaolin --nvdiffrast\n    \n\n## Examples\n\nTRELLIS provides straightforward ways to generate 3D assets. Here's a minimal Python example for image-to-3D generation:\n\npython\nimport os\nimport imageio\nfrom PIL import Image\nfrom trellis.pipelines import TrellisImageTo3DPipeline\nfrom trellis.utils import render_utils, postprocessing_utils\n\n# Load a pipeline from a model folder or a Hugging Face model hub.\npipeline = TrellisImageTo3DPipeline.from_pretrained(\"microsoft/TRELLIS-image-large\")\npipeline.cuda()\n\n# Load an image\nimage = Image.open(\"assets/example_image/T.png\")\n\n# Run the pipeline\noutputs = pipeline.run(image, seed=1)\n\n# Render the outputs and save as videos\nvideo = render_utils.render_video(outputs['gaussian'][0])['color']\nimageio.mimsave(\"sample_gs.mp4\", video, fps=30)\n\n# Extract GLB files\nglb = postprocessing_utils.to_glb(\n    outputs['gaussian'][0],\n    outputs['mesh'][0],\n    simplify=0.95,\n    texture_size=1024,\n)\nglb.export(\"sample.glb\")\n\n# Save Gaussians as PLY files\noutputs['gaussian'][0].save_ply(\"sample.ply\")\n\nThis example demonstrates loading a pre-trained model, taking an input image, generating 3D assets in various formats, and saving them as videos, GLB, and PLY files.\n\nAdditionally, TRELLIS offers a web demo based on Gradio. After installing demo-specific dependencies (`. ./setup.sh --demo`), you can run it with `python app.py`.\n\n## Why Use TRELLIS\n\nTRELLIS stands out as a leading solution for 3D generation due to several compelling features:\n\n*   **High Quality**: It consistently produces diverse 3D assets with exceptional shape and texture details.\n*   **Versatility**: TRELLIS accepts both text and image prompts, generating a wide array of final 3D representations, including Radiance Fields, 3D Gaussians, and meshes, to suit diverse downstream applications.\n*   **Flexible Editing**: The platform allows for easy modifications of generated 3D assets, such as creating variants of an object or performing local edits.\n*   **Scalable Models**: It leverages large-scale pre-trained models, some with up to 2 billion parameters, trained on an extensive dataset of 500K diverse 3D objects.\n*   **Cutting-edge Research**: Backed by a CVPR'25 Spotlight paper, TRELLIS represents the forefront of 3D generative AI research.\n\n## Links\n\n*   **GitHub Repository**: [TRELLIS](https://github.com/microsoft/TRELLIS){:target=\"_blank\"}\n*   **Project Page**: [TRELLIS Project Page](https://microsoft.github.io/TRELLIS/){:target=\"_blank\"}\n*   **Live Demo**: [Hugging Face Live Demo](https://huggingface.co/spaces/Microsoft/TRELLIS){:target=\"_blank\"}","metrics":{"detailViews":41,"githubClicks":7},"dates":{"published":null,"modified":"2026-04-01T07:33:20.000Z"}}