TRELLIS

Structured 3D Latents
for Scalable and Versatile 3D Generation

TRELLIS is a large 3D asset generation model. It takes in text or image prompts and generates high-quality 3D assets in various formats, such as Radiance Fields, 3D Gaussians, and meshes. The cornerstone of TRELLIS is a unified Structured LATent (SLAT) representation that allows decoding to different output formats and Rectified Flow Transformers tailored for SLAT as the powerful backbones. We provide large-scale pre-trained models with up to 2 billion parameters on a large 3D asset dataset of 500K diverse objects. TRELLIS significantly surpasses existing methods, including recent ones at similar scales, and showcases flexible output format selection and local 3D editing capabilities which were not offered by previous models. ***Check out our [Project Page](https://microsoft.github.io/TRELLIS/) for more videos and interactive demos!*** ## 🌟 Features - **High Quality**: It produces diverse 3D assets at high quality with intricate shape and texture details. - **Versatility**: It takes text or image prompts and can generate various final 3D representations including but not limited to *Radiance Fields*, *3D Gaussians*, and *meshes*, accommodating diverse downstream requirements. - **Flexible Editing**: It allows for easy editings of generated 3D assets, such as generating variants of the same object or local editing of the 3D asset. ## ⏩ Updates **03/25/2025** - Release training code. - Release **TRELLIS-text** models and asset variants generation. - Examples are provided as [example_text.py](example_text.py) and [example_variant.py](example_variant.py). - Gradio demo is provided as [app_text.py](app_text.py). - *Note: It is always recommended to do text to 3D generation by first generating images using text-to-image models and then using TRELLIS-image models for 3D generation. Text-conditioned models are less creative and detailed due to data limitations.* **12/26/2024** - Release [**TRELLIS-500K**](https://github.com/microsoft/TRELLIS#-dataset) dataset and toolkits for data preparation. **12/18/2024** - Implementation of multi-image conditioning for **TRELLIS-image** model. ([#7](https://github.com/microsoft/TRELLIS/issues/7)). This is based on tuning-free algorithm without training a specialized model, so it may not give the best results for all input images. - Add Gaussian export in `app.py` and `example.py`. ([#40](https://github.com/microsoft/TRELLIS/issues/40)) ## 📦 Installation ### Prerequisites - **System**: The code is currently tested only on **Linux**. For windows setup, you may refer to [#3](https://github.com/microsoft/TRELLIS/issues/3) (not fully tested). - **Hardware**: An NVIDIA GPU with at least 16GB of memory is necessary. The code has been verified on NVIDIA A100 and A6000 GPUs. - **Software**: - The [CUDA Toolkit](https://developer.nvidia.com/cuda-toolkit-archive) is needed to compile certain submodules. The code has been tested with CUDA versions 11.8 and 12.2. - [Conda](https://docs.anaconda.com/miniconda/install/#quick-command-line-install) is recommended for managing dependencies. - Python version 3.8 or higher is required. ### Installation Steps 1. Clone the repo: ```sh git clone --recurse-submodules https://github.com/microsoft/TRELLIS.git cd TRELLIS ``` 2. Install the dependencies: **Before running the following command there are somethings to note:** - By adding `--new-env`, a new conda environment named `trellis` will be created. If you want to use an existing conda environment, please remove this flag. - By default the `trellis` environment will use pytorch 2.4.0 with CUDA 11.8. If you want to use a different version of CUDA (e.g., if you have CUDA Toolkit 12.2 installed and do not want to install another 11.8 version for submodule compilation), you can remove the `--new-env` flag and manually install the required dependencies. Refer to [PyTorch](https://pytorch.org/get-started/previous-versions/) for the installation command. - If you have multiple CUDA Toolkit versions installed, `PATH` should be set to the correct version before running the command. For example, if you have CUDA Toolkit 11.8 and 12.2 installed, you should run `export PATH=/usr/local/cuda-11.8/bin:$PATH` before running the command. - By default, the code uses the `flash-attn` backend for attention. For GPUs do not support `flash-attn` (e.g., NVIDIA V100), you can remove the `--flash-attn` flag to install `xformers` only and set the `ATTN_BACKEND` environment variable to `xformers` before running the code. See the [Minimal Example](#minimal-example) for more details. - The installation may take a while due to the large number of dependencies. Please be patient. If you encounter any issues, you can try to install the dependencies one by one, specifying one flag at a time. - If you encounter any issues during the installation, feel free to open an issue or contact us. Create a new conda environment named `trellis` and install the dependencies: ```sh . ./setup.sh --new-env --basic --xformers --flash-attn --diffoctreerast --spconv --mipgaussian --kaolin --nvdiffrast ``` The detailed usage of `setup.sh` can be found by running `. ./setup.sh --help`. ``` … ``` ## 🤖 Pretrained Models We provide the following pretrained models: | Model | Description | #Params | Download | | --- | --- | --- | --- | | TRELLIS-image-large | Large image-to-3D model | 1.2B | [Download](https://huggingface.co/microsoft/TRELLIS-image-large) | | TRELLIS-text-base | Base text-to-3D model | 342M | [Download](https://huggingface.co/microsoft/TRELLIS-text-base) | | TRELLIS-text-large | Large text-to-3D model | 1.1B | [Download](https://huggingface.co/microsoft/TRELLIS-text-large) | | TRELLIS-text-xlarge | Extra-large text-to-3D model | 2.0B | [Download](https://huggingface.co/microsoft/TRELLIS-text-xlarge) | *Note: It is always recommended to use the image conditioned version of the models for better performance.* *Note: All VAEs are included in **TRELLIS-image-large** model repo.* The models are hosted on Hugging Face. You can directly load the models with their repository names in the code: ```python TrellisImageTo3DPipeline.from_pretrained("microsoft/TRELLIS-image-large") ``` If you prefer loading the model from local, you can download the model files from the links above and load the model with the folder path (folder structure should be maintained): ```python TrellisImageTo3DPipeline.from_pretrained("/path/to/TRELLIS-image-large") ``` ## 💡 Usage ### Minimal Example Here is an [example](example.py) of how to use the pretrained models for 3D asset generation. ``` … ``` After running the code, you will get the following files: - `sample_gs.mp4`: a video showing the 3D Gaussian representation - `sample_rf.mp4`: a video showing the Radiance Field representation - `sample_mesh.mp4`: a video showing the mesh representation - `sample.glb`: a GLB file containing the extracted textured mesh - `sample.ply`: a PLY file containing the 3D Gaussian representation ### Web Demo [app.py](app.py) provides a simple web demo for 3D asset generation. Since this demo is based on [Gradio](https://gradio.app/), additional dependencies are required: ```sh . ./setup.sh --demo ``` After installing the dependencies, you can run the demo with the following command: ```sh python app.py ``` Then, you can access the demo at the address shown in the terminal. ## 📚 Dataset We provide **TRELLIS-500K**, a large-scale dataset containing 500K 3D assets curated from [Objaverse(XL)](https://objaverse.allenai.org/), [ABO](https://amazon-berkeley-objects.s3.amazonaws.com/index.html), [3D-FUTURE](https://tianchi.aliyun.com/specials/promotion/alibaba-3d-future), [HSSD](https://huggingface.co/datasets/hssd/hssd-models), and [Toys4k](https://github.com/rehg-lab/lowshot-shapebias/tree/main/toys4k), filtered based on aesthetic scores. Please refer to the [dataset README](DATASET.md) for more details. ## 🏋️‍♂️ Training TRELLIS’s training framework is organized to provide a flexible and modular approach to building and fine-tuning large-scale 3D generation models. The training code is centered around `train.py` and is structured into several directories to clearly separate dataset handling, model components, training logic, and visualization utilities. ### Code Structure - **train.py**: Main entry point for training. - **trellis/datasets**: Dataset loading and preprocessing. - **trellis/models**: Different models and their components. - **trellis/modules**: Custom modules for various models. - **trellis/pipelines**: Inference pipelines for different models. - **trellis/renderers**: Renderers for different 3D representations. - **trellis/representations**: Different 3D representations. - **trellis/trainers**: Training logic for different models. - **trellis/utils**: Utility functions for training and visualization. ### Training Setup 1. **Prepare the Environment:** - Ensure all training dependencies are installed. - Use a Linux system with an NVIDIA GPU (The models are trained on NVIDIA A100 GPUs). - For distributed training, verify that your nodes can communicate through the designated master address and port. 2. **Dataset Preparation:** - Organize your dataset similar to TRELLIS-500K. Specify your dataset path using the `--data_dir` argument when launching training. 3. **Configuration Files:** - Training hyperparameters and model architectures are defined in configuration files under the `configs/` directory. - Example configuration files include: | Config | Pretained Model | Description | | --- | --- | --- | | [`vae/ss_vae_conv3d_16l8_fp16.json`](configs/vae/ss_vae_conv3d_16l8_fp16.json) | [Encoder](https://huggingface.co/microsoft/TRELLIS-image-large/blob/main/ckpts/ss_enc_conv3d_16l8_fp16.safetensors) [Decoder](https://huggingface.co/microsoft/TRELLIS-image-large/blob/main/ckpts/ss_dec_conv3d_16l8_fp16.safetensors) | Sparse structure VAE | | [`vae/slat_vae_enc_dec_gs_swin8_B_64l8_fp16.json`](configs/vae/slat_vae_enc_dec_gs_swin8_B_64l8_fp16.json) | [Encoder](https://huggingface.co/microsoft/TRELLIS-image-large/blob/main/ckpts/slat_enc_swin8_B_64l8_fp16.safetensors) [Decoder](https://huggingface.co/microsoft/TRELLIS-image-large/blob/main/ckpts/slat_dec_gs_swin8_B_64l8gs32_fp16.safetensors) | SLat VAE with Gaussian Decoder | | [`vae/slat_vae_dec_rf_swin8_B_64l8_fp16.json`](configs/vae/slat_vae_dec_rf_swin8_B_64l8_fp16.json) | [Decoder](https://huggingface.co/microsoft/TRELLIS-image-large/blob/main/ckpts/slat_dec_rf_swin8_B_64l8r16_fp16.safetensors) | SLat Radiance Field Decoder | | [`vae/slat_vae_dec_mesh_swin8_B_64l8_fp16.json`](configs/vae/slat_vae_dec_mesh_swin8_B_64l8_fp16.json) | [Decoder](https://huggingface.co/microsoft/TRELLIS-image-large/blob/main/ckpts/slat_dec_mesh_swin8_B_64l8m256c_fp16.safetensors) | SLat Mesh Decoder | | [`generation/ss_flow_img_dit_L_16l8_fp16.json`](configs/generation/ss_flow_img_dit_L_16l8_fp16.json) | [Denoiser](https://huggingface.co/microsoft/TRELLIS-image-large/blob/main/ckpts/ss_flow_img_dit_L_16l8_fp16.safetenso