ModelAufgelistetExtern

Sapiens2 Pretrain 0.1b

sapiens2-license

Quellehuggingface.co/facebook/sapiens2-pretrain-0.1b/tree/b16fc30feddc2cf9330b2980a26a8cc91f51e697

ArtOtherVersionRevision b16fc30BBewertung

Modellquelle

Art: Other
Dateigröße: 435 MB
Version: vRevision b16fc30
Aktualisiert: 22. Okt. 2026
Downloads: 646
Quelle: Hugging Face

Quellenbeschreibung

Sapiens2-0.1B

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 0.1B 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_0.1b_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_0.1b", img_size=(1024, 768), patch_size=16).eval().cuda()  # img_size is (H, W)
ckpt_path = hf_hub_download(repo_id="facebook/sapiens2-pretrain-0.1b", filename="sapiens2_0.1b_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	0.114 B
FLOPs	0.342 T
Embedding dim	768
Layers	12
Attention heads	12
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 (this)	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	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

Hugging FacePrimärVersion b16fc30feddc2cf9330b2980a26a8cc91f51e697

huggingface.co/facebook/sapiens2-pretrain-0.1b/tree/b16fc30feddc2cf9330b2980a26a8cc91f51e697

Verifiziert 22. Okt.

Modellartefakte

2 Artefakte

model.safetensors

safetensors · 435 MB · SHA-256 66f30b8b5b0d…9808 · Hugging Face

Herunterladen

sapiens2_0.1b_pretrain.safetensors

safetensors · 435 MB · SHA-256 66f30b8b5b0d…9808 · Hugging Face

Herunterladen

Quellenauszüge

3 Auszüge

Readme5. Aug.huggingface.co/facebook/sapiens2-pretrain-0.1b

--- 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 --- # Sapiens2-0.1B 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 **0.1B 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_0.1b_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_0.1b", img_size=(1024, 768), patch_size=16).eval().cuda() # img_size is (H, W) ckpt_path = hf_hub_download(repo_id="facebook/sapiens2-pretrain-0.1b", filename="sapiens2_0.1b_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 | 0.114 B | | FLOPs | 0.342 T | | Embedding dim | 768 | | Layers | 12 | | Attention heads | 12 | | Pretraining resolution | 1024 × 768 (H × W) | | Patch size | 16 | | Pre...

Note22. Okt.huggingface.co/facebook/sapiens2-pretrain-0.1b

Source context: 646 downloads · 11 likes · Pipeline image-feature-extraction · Library sapiens2 · Repo facebook/sapiens2-pretrain-0.1b

Note5. Aug.huggingface.co/facebook/sapiens2-pretrain-0.1b

Source context: 446 downloads · 8 likes · Pipeline image-feature-extraction · Library sapiens2 · Repo facebook/sapiens2-pretrain-0.1b