MatLat / README.md
32V's picture
Add model card, CC BY-NC 4.0 license, and checksums
d1fc522 verified
|
Raw
History Blame Contribute Delete
2.22 kB
---
library_name: pytorch
license: cc-by-nc-4.0
tags:
- pbr
- texture-generation
- material-generation
- 3d
- matlat
---
# MatLat Pretrained Checkpoints
Pretrained submission-version checkpoints for
[MatLat: Material Latent Space for PBR Texture Generation](https://arxiv.org/abs/2512.17302).
- `matvae_v.ours.pt`: MatVAE material autoencoder checkpoint (`global_step=200000`).
- `matdiff_v.ours.safetensors`: MatDiff text- and geometry-conditioned diffusion checkpoint.
Use them with the [official code](https://github.com/32V/mcgen).
## Download
```bash
mkdir -p checkpoints
hf download 32V/MatLat \
matvae_v.ours.pt \
matdiff_v.ours.safetensors \
--revision v1.0.0 \
--local-dir checkpoints
```
## Inference
Run from the root of the MatLat code repository:
```bash
python inference.py \
--config configs/submission/matdiff_v.ours.yaml \
--weights checkpoints/matdiff_v.ours.safetensors \
--mesh assets/motorcycle_cafe_racer/motorcycle_cafe_racer.obj \
--prompt "a matte olive green cafe racer motorcycle with brushed steel parts" \
--guidance 5.0 \
--steps 30 \
--seed 42 \
--precision bf16 \
--out outputs/demo
```
The MatVAE path and submission camera directions are selected by
`configs/submission/matdiff_v.ours.yaml`.
## License
The MatLat checkpoint weights are released under the
[Creative Commons Attribution-NonCommercial 4.0 International License](https://creativecommons.org/licenses/by-nc/4.0/)
(CC BY-NC 4.0). The license permits sharing and adaptation with appropriate
attribution for non-commercial purposes. It does not relicense third-party
software or model dependencies used by the official code.
## File Integrity
```text
f2c0d886823d7f11fe97220503ce08069e7c1b84915b27597a198bdce307e1e9 matvae_v.ours.pt
4f464112834f3a3d621cb780078e341026a62f700cec04ad7a20bc2d414dbb43 matdiff_v.ours.safetensors
```
## Citation
```bibtex
@inproceedings{yeo2026matlat,
title = {MatLat: Material Latent Space for PBR Texture Generation},
author = {Yeo, Kyeongmin and Min, Yunhong and Kim, Jaihoon and Sung, Minhyuk},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2026},
}
```