README.md

---
license: other
license_name: sapiens2-license
license_link: https://github.com/facebookresearch/sapiens2/blob/main/LICENSE.md
pipeline_tag: image-feature-extraction
library_name: sapiens
tags:
  - sapiens
  - sapiens2
  - vision-transformer
  - human-centric
  - pretrained-backbone
  - feature-extraction
---

# Sapiens2-1B

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, and pointmaps.

This repository contains the **1B parameter pretrained backbone**. It produces dense per-patch features suitable for fine-tuning downstream task heads.

- 📄 **Paper:** [arXiv:2604.21681](https://arxiv.org/pdf/2604.21681)
- 🌐 **Project Page:** [rawalkhirodkar.github.io/sapiens2](https://rawalkhirodkar.github.io/sapiens2)
- 💻 **Code:** [github.com/facebookresearch/sapiens2](https://github.com/facebookresearch/sapiens2)

## Model Details

- **Developed by:** Meta
- **Model type:** Vision Transformer
- **License:** [Sapiens2 License](https://github.com/facebookresearch/sapiens2/blob/main/LICENSE.md)
- **Task:** pretrain
- **Format:** safetensors
- **File:** `sapiens2_1b_pretrain.safetensors`

## Quick Start

Install the [Sapiens2 repo](https://github.com/facebookresearch/sapiens2) (`pip install -e .`).

```python
import torch
from huggingface_hub import hf_hub_download
from safetensors.torch import load_file
from sapiens.backbones.standalone.sapiens2 import Sapiens2

# Build the model and load the pretrained checkpoint
model = Sapiens2(arch="sapiens2_1b", img_size=(1024, 768), patch_size=16).eval().cuda()  # img_size is (H, W)
ckpt_path = hf_hub_download(repo_id="facebook/sapiens2-pretrain-1b", filename="sapiens2_1b_pretrain.safetensors")
model.load_state_dict(load_file(ckpt_path))

# Forward pass on a single image (RGB; ImageNet normalization recommended)
x = torch.randn(1, 3, 1024, 768).cuda()
with torch.no_grad():
    features = model(x)[0]  # dense backbone features: (B, num_tokens, embed_dim)
```

## Model Card

| Field | Value |
|-------|-------|
| Architecture | Sapiens2 ViT (RoPE, GQA, SwiGLU, RMSNorm, QK-norm) |
| Parameters | 1.462 B |
| FLOPs | 4.715 T |
| Embedding dim | 1536 |
| Layers | 40 |
| Attention heads | 24 |
| Pretraining resolution | 1024 × 768 (H × W) |
| Patch size | 16 |
| Pretraining data | 1B human images |

### Sapiens2 Family

| Model | Params | FLOPs | Embed dim | Layers | Heads |
|-------|--------|-------|-----------|--------|-------|
| [Sapiens2-0.1B](https://huggingface.co/facebook/sapiens2-pretrain-0.1b) | 0.114 B | 0.342 T | 768 | 12 | 12 |
| [Sapiens2-0.4B](https://huggingface.co/facebook/sapiens2-pretrain-0.4b) | 0.398 B | 1.260 T | 1024 | 24 | 16 |
| [Sapiens2-0.8B](https://huggingface.co/facebook/sapiens2-pretrain-0.8b) | 0.818 B | 2.592 T | 1280 | 32 | 16 |
| **Sapiens2-1B** *(this)* | 1.462 B | 4.715 T | 1536 | 40 | 24 |
| [Sapiens2-1B-4K](https://huggingface.co/facebook/sapiens2-pretrain-1b-4k) | 1.607 B | — | 1536 | 40 | 24 |
| [Sapiens2-5B](https://huggingface.co/facebook/sapiens2-pretrain-5b) | 5.071 B | 15.722 T | 2432 | 56 | 32 |

See the [Sapiens2 Collection](https://huggingface.co/collections/facebook/sapiens2) for all variants and downstream task checkpoints (pose, segmentation, normals, pointmaps).

## Intended Use

- Feature extraction for human-centric downstream tasks
- Initialization for fine-tuning task heads (pose, segmentation, normals, pointmap)
- Research on human-centric vision

## License

Released under the [Sapiens2 License](https://github.com/facebookresearch/sapiens2/blob/main/LICENSE.md).

## Citation

```bibtex
@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}
}
```