---
title: sapiens2-pose-5b
canonical_url: "https://www.modelscope.cn/models/facebook/sapiens2-pose-5b"
md_url: "https://www.modelscope.cn/models/facebook/sapiens2-pose-5b.md"
repository: facebook/sapiens2-pose-5b
last_updated: 2026-06-15
license: other
model_type:
  - sapiens2
architectures:
  - Sapiens2ForPoseEstimation
base_model:
  - facebook/sapiens2-pretrain-5b
base_model_relation: finetune
parameters: 5.1B
tensor_type:
  - F32
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 89
stars: 0
tags:
  - sapiens
  - sapiens2
  - human-centric
  - pose
  - transformers
---

# sapiens2-pose-5b

> sapiens2-pose-5b - facebook 在 ModelScope 开源的模型。308-keypoint top-down pose estimation including detailed face (274 keypoints), hand, and foot keypoints. Predictions follow the Sociopticon keypoint format.

facebook/sapiens2-pose-5b 是 ModelScope 魔搭社区上的 5.1B 参数机器学习模型，采用 other 许可，基于 facebook/sapiens2-pretrain-5b 构建。

- **Repository**: facebook/sapiens2-pose-5b
- **License**: other
- **Parameters**: 5.1B
- **Base model**: facebook/sapiens2-pretrain-5b
- **Tags**: sapiens, sapiens2, human-centric, pose, transformers
- **Downloads**: 89
- **Stars**: 0
- **Last updated**: 2026-06-15

Source: https://www.modelscope.cn/models/facebook/sapiens2-pose-5b

---

# Sapiens2-5B-Pose

308-keypoint top-down pose estimation including detailed face (274 keypoints), hand, and foot keypoints. Predictions follow the [Sociopticon keypoint format](https://github.com/facebookresearch/sapiens2/blob/main/sapiens/pose/configs/_base_/keypoints308.py).

This repository contains the **5B Pose Estimation** checkpoint, finetuned from the [Sapiens2-5B pretrained backbone](https://huggingface.co/facebook/sapiens2-pretrain-5b).

Pose is top-down — it requires bounding boxes from a person detector. We use [RTMDet](https://github.com/open-mmlab/mmdetection/tree/main/configs/rtmdet).

- 📄 **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:** pose
- **Base model:** [facebook/sapiens2-pretrain-5b](https://huggingface.co/facebook/sapiens2-pretrain-5b)
- **Format:** safetensors
- **File:** `sapiens2_5b_pose.safetensors`

## Quick Start

Install the [Sapiens2 repo](https://github.com/facebookresearch/sapiens2) (`pip install -e .`), download the checkpoint, and run the demo:

```bash
# 1. Download the checkpoint to $SAPIENS_CHECKPOINT_ROOT/pose/
hf download facebook/sapiens2-pose-5b sapiens2_5b_pose.safetensors \
    --local-dir ~/sapiens2_host/pose

# 2. Run the demo (edit INPUT, OUTPUT, and MODEL_NAME inside the script)
cd $SAPIENS_ROOT/sapiens/pose
./scripts/demo/keypoints308.sh
```

See the [Pose Estimation guide](https://github.com/facebookresearch/sapiens2/blob/main/docs/POSE.md) for details on inputs, outputs, and visualization options.

## Model Card

| Field | Value |
|-------|-------|
| Architecture | Sapiens2 ViT backbone + Pose Estimation head |
| Backbone parameters | 5.071 B |
| Backbone FLOPs | 15.722 T |
| Embedding dim | 2432 |
| Layers | 56 |
| Attention heads | 32 |
| Inference resolution | 1024 × 768 (H × W) |
| Patch size | 16 |

### Sapiens2-Pose Family

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

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

## Intended Use

- Pose Estimation on human-centric imagery
- 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}
}
```