Aller au contenu
ModelPrésentéExterne
Télécharger

MeshAnything

MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers

TypeOtherVersionRevision d023238BClasse

Source du modèle

Type
Other
Taille du fichier
2,22 GB
Version
vRevision d023238
Mis à jour
15 sept. 2026
Téléchargements
58
Source
Hugging Face

Extrait de la source

MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers

Sources

1 source
Hugging FacePrincipalVersion d023238e47212c8800380ef008f4f7822824a705
huggingface.co/Yiwen-ntu/MeshAnything/tree/d023238e47212c8800380ef008f4f7822824a705

Vérifié 1 sept.

Artefacts du modèle

1 artefact

MeshAnything_350m.pth

pth · 2,22 GB · SHA-256 f2de0cbd19d7…5f6b · Hugging Face

Download file

Extraits de sources

2 extraits

--- pipeline_tag: image-to-3d library_name: mesh-anything --- <p align="center"> <h3 align="center"><strong>MeshAnything:<br> Artist-Created Mesh Generation<br> with Autoregressive Transformers</strong></h3> <p align="center"> <a href="https://buaacyw.github.io/">Yiwen Chen</a><sup>1,2*</sup>, <a href="https://tonghe90.github.io/">Tong He</a><sup>2†</sup>, <a href="https://dihuang.me/">Di Huang</a><sup>2</sup>, <a href="https://ywcmaike.github.io/">Weicai Ye</a><sup>2</sup>, <a href="https://ch3cook-fdu.github.io/">Sijin Chen</a><sup>3</sup>, <a href="https://me.kiui.moe/">Jiaxiang Tang</a><sup>4</sup><br> <a href="https://chenxin.tech/">Xin Chen</a><sup>5</sup>, <a href="https://caizhongang.github.io/">Zhongang Cai</a><sup>6</sup>, <a href="https://scholar.google.com.hk/citations?user=jZH2IPYAAAAJ&hl=en">Lei Yang</a><sup>6</sup>, <a href="https://www.skicyyu.org/">Gang Yu</a><sup>7</sup>, <a href="https://guosheng.github.io/">Guosheng Lin</a><sup>1†</sup>, <a href="https://icoz69.github.io/">Chi Zhang</a><sup>8†</sup> <br> <sup>*</sup>Work done during a research internship at Shanghai AI Lab. <br> <sup>†</sup>Corresponding authors. <br> <sup>1</sup>S-Lab, Nanyang Technological University, <sup>2</sup>Shanghai AI Lab, <br> <sup>3</sup>Fudan University, <sup>4</sup>Peking University, <sup>5</sup>University of Chinese Academy of Sciences, <br> <sup>6</sup>SenseTime Research, <sup>7</sup>Stepfun, <sup>8</sup>Westlake University </p> ## Release - [6/17] 🔥🔥 We released the 350m version of **MeshAnything**. ## Contents - [Release](#release) - [Contents](#contents) - [Installation](#installation) - [Usage](#usage) - [Important Notes](#important-notes) - [TODO](#todo) - [Acknowledgement](#acknowledgement) - [BibTeX](#bibtex) ## Installation Our environment has been tested on Ubuntu 22, CUDA 11.8 with A100, A800 and A6000. 1. Clone our repo and create conda environment ``` git clone https://github.com/buaacyw/MeshAnything.git && cd MeshAnything conda create -n MeshAnything python==3.10.13 conda activate MeshAnything pip install torch==2.1.1 torchvision==0.16.1 torchaudio==2.1.1 --index-url https://download.pytorch.org/whl/cu118 pip install -r requirements.txt pip install flash-attn --no-build-isolation ``` ## Usage ### Local Gradio Demo <a href='https://github.com/gradio-app/gradio'><img src='https://img.shields.io/github/stars/...

Source context: 58 downloads · 14 likes · Pipeline image-to-3d · Library mesh-anything · Repo Yiwen-ntu/MeshAnything