Instructions to use OJ-1/sapiens2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sapiens
How to use OJ-1/sapiens2 with sapiens:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- sapiens2
How to use OJ-1/sapiens2 with sapiens2:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
metadata
license: other
license_name: sapiens2-license
license_link: https://github.com/facebookresearch/sapiens2/blob/main/LICENSE.md
library_name: sapiens
tags:
- sapiens
- sapiens2
- human-centric
- vision-transformer
Sapiens2
Sapiens2 is a family of high-resolution vision transformers pretrained on 1 billion human images — designed for human-centric tasks such as pose estimation, body-part segmentation, surface normals, pointmaps, and human matting.
This is the index repository: each variant lives in its own model repo (linked below).
- 📄 Paper: arXiv:2604.21681
- 🌐 Project Page: rawalkhirodkar.github.io/sapiens2
- 💻 Code: github.com/facebookresearch/sapiens2
- 📚 Collection: Sapiens2 on HuggingFace
Pretrained Backbones
| Model | Params | Repository |
|---|---|---|
| Sapiens2-0.1B | 0.114 B | facebook/sapiens2-pretrain-0.1b |
| Sapiens2-0.4B | 0.398 B | facebook/sapiens2-pretrain-0.4b |
| Sapiens2-0.8B | 0.818 B | facebook/sapiens2-pretrain-0.8b |
| Sapiens2-1B | 1.462 B | facebook/sapiens2-pretrain-1b |
| Sapiens2-1B (4K) | 1.607 B | facebook/sapiens2-pretrain-1b-4k |
| Sapiens2-5B | 5.071 B | facebook/sapiens2-pretrain-5b |
Task Checkpoints
Pose Estimation
| Model | Repository |
|---|---|
| Sapiens2-0.4B | facebook/sapiens2-pose-0.4b |
| Sapiens2-0.8B | facebook/sapiens2-pose-0.8b |
| Sapiens2-1B | facebook/sapiens2-pose-1b |
| Sapiens2-5B | facebook/sapiens2-pose-5b |
Body-Part Segmentation
| Model | Repository |
|---|---|
| Sapiens2-0.4B | facebook/sapiens2-seg-0.4b |
| Sapiens2-0.8B | facebook/sapiens2-seg-0.8b |
| Sapiens2-1B | facebook/sapiens2-seg-1b |
| Sapiens2-5B | facebook/sapiens2-seg-5b |
Surface Normal Estimation
| Model | Repository |
|---|---|
| Sapiens2-0.4B | facebook/sapiens2-normal-0.4b |
| Sapiens2-0.8B | facebook/sapiens2-normal-0.8b |
| Sapiens2-1B | facebook/sapiens2-normal-1b |
| Sapiens2-5B | facebook/sapiens2-normal-5b |
Pointmap Estimation
| Model | Repository |
|---|---|
| Sapiens2-0.4B | facebook/sapiens2-pointmap-0.4b |
| Sapiens2-0.8B | facebook/sapiens2-pointmap-0.8b |
| Sapiens2-1B | facebook/sapiens2-pointmap-1b |
| Sapiens2-5B | facebook/sapiens2-pointmap-5b |
Human Matting
| Model | Repository |
|---|---|
| Sapiens2-1B | facebook/sapiens2-matting-1b |
License
Released under the Sapiens2 License.
Citation
@article{khirodkarsapiens2,
title={Sapiens2},
author={Khirodkar, Rawal and Wen, He and Martinez, Julieta and Dong, Yuan and Su, Zhaoen and Saito, Shunsuke},
journal={arXiv preprint arXiv:2604.21681},
year={2026}
}