Delete README.md

README.md

@@ -1,99 +0,0 @@
----
-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 `3d-rs` runtime.
-
-The package converts the original TripoSR checkpoint/config pair into a stable runtime layout with explicit provenance and integrity metadata.
-
-## Model Details
-
-- Model family: `triposr`
-- Canonical file: `model.safetensors`
-- Tensor count: `549`
-- Primary runtime target: Lux3D `3d-rs`
-- Typical output: mesh export (`.obj`)
-
-## Included Files
-
-- `model.safetensors`: canonical model weights for runtime loading
-- `resolved_config.json`: normalized JSON snapshot of the effective TripoSR config
-- `manifest.json`: provenance metadata for the canonical package
-- `checksums.json`: integrity data for the files in this package
-
-## Usage With Lux3D
-
-This folder is designed to be uploaded as a standalone Hugging Face model repository and then restored into:
-
-```text
-<repo-root>/3d/canonical-weights/triposr/
-```
-
-The Lux3D CLI will validate and use the package. The example below assumes you run it from the `3d-rs/` directory:
-
-```powershell
-cargo run -p lux3d-cli -- inspect --repo-root .. triposr
-cargo run -p lux3d-cli -- run --repo-root .. triposr --source ../tp/3d/TripoSR/examples/horse.png --mc-resolution 256 --mc-threshold 25.0 --output ../3d/_generated/triposr.obj
-```
-
-## Provenance
-
-- Upstream source model: [`stabilityai/TripoSR`](https://huggingface.co/stabilityai/TripoSR)
-- Canonicalization flow: `3d-rs/tools/python_baseline/normalize_weights.py`
-- Raw source files expected by Lux3D before normalization:
-  - `3d/models/stabilityai-TripoSR/model.ckpt`
-  - `3d/models/stabilityai-TripoSR/config.yaml`
-
-The exact source checksum set is recorded in `manifest.json`. The integrity of the uploaded package is recorded in `checksums.json`.
-
-## Intended Use
-
-This package is intended for:
-
-- single-image 3D reconstruction in Lux3D
-- mesh generation workflows using TripoSR canonical weights
-- reproducible local/runtime validation
-
-This package is not meant to replace the full upstream TripoSR repository. It is the runtime-focused canonical weight package for Lux3D.
-
-## Limitations
-
-- Verified Lux3D 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
-
-The upstream TripoSR model and code are distributed under MIT.
-
-- Upstream model page: [`stabilityai/TripoSR`](https://huggingface.co/stabilityai/TripoSR)
-- Local package notice: [LICENSE](LICENSE)
-
-Retain upstream attribution when redistributing the package.
-
-## Citation
-
-If you use TripoSR in research, cite the upstream work:
-
-```bibtex
-@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}
-}
-```