InstantMesh
TencentInstantMesh is Tencent ARC Lab's image-to-3D model. A multi-view diffusion model first draws several views of the object in a single image, and a sparse-view reconstruction model then turns them into a textured 3D mesh, the whole run taking about ten seconds.
Released April 2024; the repository was last updated in January 2025 and no later InstantMesh release exists. The multi-view stage is a fine-tuned Zero123++ v1.2, whose base pipeline the inference script downloads from SUDO AI's Hugging Face account.
Openness
2 medium confidence- weights
- open (the four reconstruction checkpoints and the fine-tuned Zero123++ UNet download from TencentARC/InstantMesh without a gate)
- data
- described (trained on Objaverse renders; the README says the training set is not provided because of its size)
- code
- open (training code for the reconstruction models and for the Zero123++ fine-tuning is published)
- license
- Apache-2.0 (the InstantMesh code and weights, per the LICENSE and the model card)+CC-BY-NC-4.0 (Zero123++ v1.2, which run.py downloads by default for the multi-view stage and which the InstantMesh UNet fine-tunes)
InstantMesh's own code and weights are Apache 2.0, but its first stage runs Zero123++ v1.2, whose weights are licensed for non-commercial use only, and the inference script downloads them by default. Training code is published; the Objaverse renders it trained on are not.
- https://huggingface.co/api/models/TencentARC/InstantMesh?expand[]=downloads&expand[]=likes&expand[]=cardData&expand[]=gated&expand[]=lastModified&expand[]=createdAt&expand[]=siblings recorded 2026-11-12
Hugging Face API record for TencentARC/InstantMesh: gated false, files diffusion_pytorch_model.bin and four instant_mesh/instant_nerf checkpoints.
- https://huggingface.co/TencentARC/InstantMesh/raw/main/README.md recorded 2026-11-12
Card front matter "license: apache-2.0"; "We release all the code, weights, and demo of InstantMesh".
- https://ungh.cc/repos/SUDO-AI-3D/zero123plus/files/main/README.md recorded 2026-11-12
Zero123++ README: "The code is released under Apache 2.0 and the model weights are released under CC-BY-NC 4.0"; "you cannot use the model (or its derivatives) in a commercial product pipeline".
- https://ungh.cc/repos/TencentARC/InstantMesh/files/main recorded 2026-11-12
Repository file list: train.py, training configs for the NeRF and mesh variants and configs/zero123plus-finetune.yaml, and src/data/objaverse.py.
- https://ungh.cc/repos/TencentARC/InstantMesh/files/main/LICENSE recorded 2026-11-12
LICENSE body: Apache License, Version 2.0.
- https://ungh.cc/repos/TencentARC/InstantMesh/files/main/README.md recorded 2026-11-12
README: "Release inference and training code"; "We provide our training code to facilitate future research. But we cannot provide the training dataset due to its size"; a Zero123++ fine-tuning command is given.
- https://ungh.cc/repos/TencentARC/InstantMesh/files/main/run.py recorded 2026-11-12
run.py loads DiffusionPipeline.from_pretrained("sudo-ai/zero123plus-v1.2", custom_pipeline="zero123plus") and then swaps in the UNet from TencentARC/InstantMesh.
Adoption
2 high confidenceAdoption is measured as Hugging Face downloads of TencentARC/InstantMesh, the only first-party copy of the weights.
- https://huggingface.co/api/models/TencentARC/InstantMesh?expand[]=downloads&expand[]=likes&expand[]=cardData&expand[]=gated&expand[]=lastModified&expand[]=createdAt&expand[]=siblings recorded 2026-11-12
Hugging Face API record for TencentARC/InstantMesh: downloads 24072.
Capability
3 medium confidenceInstantMesh places in the upper half of the image-to-3D arena for rendered quality, just behind Hunyuan3D-2 and 2.1, and in the lower half of the board that rates mesh topology.
- https://3d-arena-3d-arena.hf.space/api/leaderboard?vote_type=render recorded 2026-11-12
Render board of 24 entries: "InstantMesh" rank 10, score 1269, 11616 votes; "Hunyuan3D-2" rank 8, "Hunyuan3D-2.1" rank 9.
- https://3d-arena-3d-arena.hf.space/api/leaderboard?vote_type=topology recorded 2026-11-12
Topology board of 22 entries: "InstantMesh" rank 16, score 1100.
Verified 2026-11-12