Sapiens2 Pretrain 5b
sapiens2-license
Modellquelle
- Art
- Other
- Dateigröße
- 18,9 GB
- Version
- vRevision 407b02b
- Aktualisiert
- 22. Okt. 2026
- Downloads
- 697
- Quelle
- Hugging Face
Quellenbeschreibung
Sapiens2-5B
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 5B parameter pretrained backbone. It produces dense per-patch features suitable for fine-tuning downstream task heads.
- 📄 Paper: arXiv:2604.21681
- 🌐 Project Page: rawalkhirodkar.github.io/sapiens2
- 💻 Code: github.com/facebookresearch/sapiens2
Model Details
- Developed by: Meta
- Model type: Vision Transformer
- License: Sapiens2 License
- Task: pretrain
- Format: safetensors
- File:
sapiens2_5b_pretrain.safetensors
Quick Start
Install the Sapiens2 repo (pip install -e .).
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_5b", img_size=(1024, 768), patch_size=16).eval().cuda() # img_size is (H, W)
ckpt_path = hf_hub_download(repo_id="facebook/sapiens2-pretrain-5b", filename="sapiens2_5b_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 | 5.071 B |
| FLOPs | 15.722 T |
| Embedding dim | 2432 |
| Layers | 56 |
| Attention heads | 32 |
| 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 | 0.114 B | 0.342 T | 768 | 12 | 12 |
| Sapiens2-0.4B | 0.398 B | 1.260 T | 1024 | 24 | 16 |
| Sapiens2-0.8B | 0.818 B | 2.592 T | 1280 | 32 | 16 |
| Sapiens2-1B | 1.462 B | 4.715 T | 1536 | 40 | 24 |
| Sapiens2-1B-4K | 1.607 B | — | 1536 | 40 | 24 |
| Sapiens2-5B (this) | 5.071 B | 15.722 T | 2432 | 56 | 32 |
See the Sapiens2 Collection 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.
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}
}
Quellen
1 Quelle
Quellen
1 QuelleVerifiziert 22. Okt.
Download files
Modellartefakte
2 Artefakte
Modellartefakte
2 Artefaktesapiens2_5b_pretrain.safetensors
safetensors · 18,9 GB · SHA-256 b6e7e0011254…9a1c · Hugging Face
Download fileQuellenauszüge
3 Auszüge
Quellenauszüge
3 Auszüge--- license: other license_name: sapiens2-license license_link: https://github.com/facebookresearch/sapiens2/blob/main/LICENSE.md pipeline_tag: image-feature-extraction library_name: sapiens2 tags: - sapiens - sapiens2 - vision-transformer - human-centric - pretrained-backbone - feature-extraction - transformers --- # Sapiens2-5B 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 **5B 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_5b_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_5b", img_size=(1024, 768), patch_size=16).eval().cuda() # img_size is (H, W) ckpt_path = hf_hub_download(repo_id="facebook/sapiens2-pretrain-5b", filename="sapiens2_5b_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 | 5.071 B | | FLOPs | 15.722 T | | Embedding dim | 2432 | | Layers | 56 | | Attention heads | 32 | | Pretraining resolution | 1024 × 768 (H × W) | | Patch size | 16 | | Pretraining d...
Source context: 697 downloads · 9 likes · Pipeline image-feature-extraction · Library sapiens2 · Repo facebook/sapiens2-pretrain-5b
Source context: 611 downloads · 7 likes · Pipeline image-feature-extraction · Library sapiens2 · Repo facebook/sapiens2-pretrain-5b
