README.md

metadata

license: mit
pipeline_tag: image-to-3d
base_model: stabilityai/TripoSR
tags:
  - lux3d
  - rust
  - candle
  - safetensors
  - canonical-weights
  - 3d
  - image-to-3d
  - mesh-generation
  - triposr

Lux3D TripoSR Canonical Weights

This repository contains the canonicalized safetensors export of the TripoSR checkpoint used by the Lux3D runtime.

Model Details

• Model family: triposr
• Canonical file: model.safetensors
• Tensor count: 549
• Primary runtime target: Lux3D runtime
• Typical output: mesh export (.obj)

Included Files

• model.safetensors
• resolved_config.json
• manifest.json
• checksums.json

Usage With Lux3D

The Lux3D CLI can validate and use the package once it is installed into your local model asset layout.

cargo run -p lux3d-cli -- inspect --repo-root <runtime-root> triposr
cargo run -p lux3d-cli -- run --repo-root <runtime-root> triposr --source <input-image> --mc-resolution 256 --mc-threshold 25.0 --output <output-file.obj>

Provenance

• Upstream source model: stabilityai/TripoSR
• Canonicalization flow: tools/python_baseline/normalize_weights.py

The exact source checksum set is recorded in manifest.json. The integrity of the uploaded package is recorded in checksums.json.

Intended Use

• single-image 3D reconstruction with Lux3D
• mesh generation workflows using canonical weights
• reproducible runtime validation

Limitations

• Verified Lux3D runtime inference currently assumes CUDA.
• This package includes canonical runtime artifacts only.
• Texture baking and other extended upstream utilities are outside the scope of this package.

License

• Upstream model page: stabilityai/TripoSR
• License file in this repository: LICENSE

Citation

@article{tripoSR2024,
  title={TripoSR: Fast 3D Object Reconstruction from a Single Image},
  author={Tochilkin, Dmitry and Pankratz, David and Liu, Zexiang and Huang, Zixuan and Letts, Adam and Li, Yangguang and Liang, Ding and Laforte, Christian and Jampani, Varun and Cao, Yan-Pei},
  journal={arXiv preprint arXiv:2403.02151},
  year={2024}
}