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: timm
tags:
- sapiens
- sapiens2
- vision-transformer
- human-centric
- pretrained-backbone
- feature-extraction
- transformers
- timm
base_model: facebook/sapiens2-pretrain-0.4b
---

> **NOTE:** This is a native **timm (EVA) remap** of [facebook/sapiens2-pretrain-0.4b](https://huggingface.co/facebook/sapiens2-pretrain-0.4b/tree/ce294175eb49429cb612bd91eb6a4a466fc2c358). Checkpoint keys have been converted to timm naming; the weights have not been fine-tuned. The original [Sapiens2 License](LICENSE.md) applies. The upstream model card is reproduced below with timm usage instructions.

# Sapiens2-0.4B

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 **0.4B 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:** `model.safetensors`

## Quick Start

Use a timm version that includes Sapiens2 support.

```python
import torch
import timm
from PIL import Image

device = "cuda" if torch.cuda.is_available() else "cpu"
model = timm.create_model(
    "hf-hub:timm/vit_large_patch16_sapiens2.fb", pretrained=True, use_naflex=False,
).eval().to(device)

data_config = timm.data.resolve_model_data_config(model)
transform = timm.data.create_transform(**data_config, is_training=False)
image = Image.open("image.jpg").convert("RGB")
x = transform(image).unsqueeze(0).to(device)

with torch.inference_mode():
    tokens = model.forward_features(x)
    cls_features = tokens[:, 0]
    patch_features = tokens[:, model.num_prefix_tokens:]  # exclude CLS and register tokens
```

`model(x)` uses CLS-token pooling by default, matching the original Sapiens2 convention.
Pass `global_pool="avg"` to `create_model` for average pooling over patch tokens.

## Model Card

| Field | Value |
|-------|-------|
| Architecture | Sapiens2 ViT (RoPE, GQA, SwiGLU, RMSNorm, QK-norm) |
| Parameters | 0.398 B |
| FLOPs | 1.260 T |
| Embedding dim | 1024 |
| Layers | 24 |
| Attention heads | 16 |
| 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** *(this)* | 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](https://huggingface.co/facebook/sapiens2-pretrain-1b) | 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}
}
```