# microsoft/trellis **Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/microsoft-trellis).** 12,977 stars · 1,254 forks · Python · MIT ## Links - GitHub: https://github.com/microsoft/TRELLIS - Homepage: https://trellis3d.github.io - awesome-repositories: https://awesome-repositories.com/repository/microsoft-trellis.md ## Topics `3d` `3d-aigc` `3d-generation` `image-to-3d` `text-to-3d` ## Description TRELLIS is a 3D generative AI model and latent diffusion framework designed to transform natural language descriptions or reference images into textured 3D assets. It operates as a text-to-3D asset generator that utilizes structured latent representations to produce high-quality 3D meshes, Gaussians, and Radiance Fields. The system functions as a multi-format 3D decoder, converting internal representations into standard exchange formats such as GLB and PLY. It also serves as a 3D asset editing tool, enabling the modification of specific regions of generated objects through targeted text or image-based prompts. The framework covers a broad range of capabilities including cross-modal conditioning and diffusion-based latent generation. It supports large-scale model training across single or multi-node GPU configurations and provides workflows for creating visual variations of existing assets. ## Tags ### Artificial Intelligence & ML - [Text-to-3D Generators](https://awesome-repositories.com/f/artificial-intelligence-ml/text-to-3d-generators.md) — Transforms natural language descriptions or reference images into high-quality textured 3D assets. - [Diffusion-Based 3D Generators](https://awesome-repositories.com/f/artificial-intelligence-ml/diffusion-based-3d-generators.md) — Uses a diffusion process to predict 3D latent representations from text or image embeddings. - [Latent Space Generative Models](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-resources/diffusion-visual-models/generative-ai-models/latent-space-generative-models.md) — Represents complex 3D geometry and texture as compressed tensors to enable scalable generation. - [3D Asset Generators](https://awesome-repositories.com/f/artificial-intelligence-ml/image-generation-models/3d-asset-generators.md) — Synthesizes detailed 3D objects with textures using text descriptions or image conditions. ([source](https://microsoft.github.io/TRELLIS/)) - [Distributed GPU Training](https://awesome-repositories.com/f/artificial-intelligence-ml/distributed-gpu-training.md) — Scales model training across multiple GPU nodes using synchronized gradient updates. - [Latent-to-Pixel Decoding](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-resources/diffusion-visual-models/generative-ai-models/latent-space-generative-models/latent-space-projections/image-to-latent-projections/latent-to-pixel-decoding.md) — Converts internal compressed 3D representations into standard exchange formats like GLB and PLY. - [Asset Variation Generators](https://awesome-repositories.com/f/artificial-intelligence-ml/image-generation-models/3d-asset-generators/asset-variation-generators.md) — Creates new versions of existing 3D assets that remain visually aligned with specified text prompts. ([source](https://microsoft.github.io/TRELLIS/)) - [Large-Scale Model Training](https://awesome-repositories.com/f/artificial-intelligence-ml/large-scale-model-training.md) — Supports large-scale generative model training across single or multi-node GPU configurations. ([source](https://cdn.jsdelivr.net/gh/microsoft/trellis@main/README.md)) - [Large Scale Training](https://awesome-repositories.com/f/artificial-intelligence-ml/large-scale-training.md) — Trains generative 3D models across single or multi-node GPU setups for improved quality. - [Multi-Format Latent Decoding](https://awesome-repositories.com/f/artificial-intelligence-ml/representation-probing/implicit-latent-representations/multi-format-latent-decoding.md) — Translates learned latent vectors into diverse outputs including 3D Gaussians, meshes, and radiance fields. ### Part of an Awesome List - [Generative 3D Modeling](https://awesome-repositories.com/f/awesome-lists/ai/generative-3d-modeling.md) — Implements a deep learning framework for synthesizing 3D meshes, Gaussians, and Radiance Fields. ### Data & Databases - [3D Scene Exporters](https://awesome-repositories.com/f/data-databases/query-translators/multi-format-exports/3d-scene-exporters.md) — Provides a pipeline to export internal 3D representations into standard exchange formats such as GLB and PLY. ### Graphics & Multimedia - [3D Asset Exporters](https://awesome-repositories.com/f/graphics-multimedia/3d-asset-exporters.md) — Converts generated 3D assets into standard industry file types such as GLB and PLY. ([source](https://cdn.jsdelivr.net/gh/microsoft/trellis@main/README.md)) - [Global Asset Variations](https://awesome-repositories.com/f/graphics-multimedia/3d-geometry-editing/global-asset-variations.md) — Provides capabilities to modify generated 3D objects to create overall visual variations. ([source](https://cdn.jsdelivr.net/gh/microsoft/trellis@main/README.md)) - [Local Region Editing](https://awesome-repositories.com/f/graphics-multimedia/3d-geometry-editing/local-region-editing.md) — Enables modification of specific regions of a 3D model using targeted prompts to refine details. ([source](https://microsoft.github.io/TRELLIS/)) - [Prompt-Based Geometry Editing](https://awesome-repositories.com/f/graphics-multimedia/3d-geometry-editing/prompt-based-geometry-editing.md) — Provides tools for modifying specific regions of 3D objects through targeted text or image-based prompts. ### Scientific & Mathematical Computing - [3D Representation Conversions](https://awesome-repositories.com/f/scientific-mathematical-computing/3d-data-processing-libraries/3d-representation-conversions.md) — Converts internal 3D latent representations into various formats like meshes, 3D Gaussians, and Radiance Fields. ([source](https://microsoft.github.io/TRELLIS/))