Skip to content
ModelListedExternal
Browse files

InstantMesh

Model card for InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models.

KindOtherVersionRevision 3d042b9Bgrade

Model source

Kind
Other
File size
1.17–1.61 GB
Version
vRevision 3d042b9
Updated
Oct 27, 2026
Downloads
49
Source
Hugging Face

Source description

InstantMesh

Model card for InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models.

Code: https://github.com/TencentARC/InstantMesh

Arxiv: https://arxiv.org/abs/2404.07191

We present InstantMesh, a feed-forward framework for instant 3D mesh generation from a single image, featuring state-of-the-art generation quality and significant training scalability. By synergizing the strengths of an off-the-shelf multiview diffusion model and a sparse-view reconstruction model based on the LRM architecture, InstantMesh is able to create diverse 3D assets within 10 seconds. To enhance the training efficiency and exploit more geometric supervisions, e.g., depths and normals, we integrate a differentiable iso-surface extraction module into our framework and directly optimize on the mesh representation. Experimental results on public datasets demonstrate that InstantMesh significantly outperforms other latest image-to-3D baselines, both qualitatively and quantitatively. We release all the code, weights, and demo of InstantMesh, with the intention that it can make substantial contributions to the community of 3D generative AI and empower both researchers and content creators.

Sources

1 source
Hugging FacePrimaryVersion 3d042b9efe4f25071f22c8e00258fa44ccf978ea
huggingface.co/younghyeon1111/InstantMesh/tree/3d042b9efe4f25071f22c8e00258fa44ccf978ea

Verified Oct 27

Download files

Model artifacts

5 artifacts

diffusion_pytorch_model.bin

bin · 1.61 GB · SHA-256 9d78d78421d1…a3c4 · Hugging Face

Download file

instant_mesh_base.ckpt

ckpt · 1.17 GB · SHA-256 22701cd25201…44b5 · Hugging Face

Download file

instant_mesh_large.ckpt

ckpt · 1.41 GB · SHA-256 329f7aae9b58…91a1 · Hugging Face

Download file

instant_nerf_base.ckpt

ckpt · 1.17 GB · SHA-256 bcbfff8be854…d9c9 · Hugging Face

Download file

instant_nerf_large.ckpt

ckpt · 1.41 GB · SHA-256 530a344ea9b8…2fb9 · Hugging Face

Download file

Source excerpts

3 excerpts

--- license: apache-2.0 tags: - image-to-3d --- # InstantMesh Model card for *InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models*. Code: https://github.com/TencentARC/InstantMesh Arxiv: https://arxiv.org/abs/2404.07191 We present InstantMesh, a feed-forward framework for instant 3D mesh generation from a single image, featuring state-of-the-art generation quality and significant training scalability. By synergizing the strengths of an off-the-shelf multiview diffusion model and a sparse-view reconstruction model based on the LRM architecture, InstantMesh is able to create diverse 3D assets within 10 seconds. To enhance the training efficiency and exploit more geometric supervisions, e.g., depths and normals, we integrate a differentiable iso-surface extraction module into our framework and directly optimize on the mesh representation. Experimental results on public datasets demonstrate that InstantMesh significantly outperforms other latest image-to-3D baselines, both qualitatively and quantitatively. We release all the code, weights, and demo of InstantMesh, with the intention that it can make substantial contributions to the community of 3D generative AI and empower both researchers and content creators.

Source context: 49 downloads · 0 likes · Pipeline image-to-3d · Library diffusers · Repo younghyeon1111/InstantMesh

Source context: 10 downloads · 0 likes · Pipeline image-to-3d · Library diffusers · Repo younghyeon1111/InstantMesh