---
title: pixio-vitl16
canonical_url: "https://www.modelscope.cn/models/facebook/pixio-vitl16"
md_url: "https://www.modelscope.cn/models/facebook/pixio-vitl16.md"
repository: facebook/pixio-vitl16
last_updated: 2026-01-06
license: "Apache License 2.0"
downloads: 79
stars: 0
---

# pixio-vitl16

> pixio-vitl16 - facebook 在 ModelScope 开源的模型。Model Card for Pixio

facebook/pixio-vitl16 是 ModelScope 魔搭社区上的机器学习模型，采用 Apache License 2.0 许可。

- **Repository**: facebook/pixio-vitl16
- **License**: Apache License 2.0
- **Downloads**: 79
- **Stars**: 0
- **Last updated**: 2026-01-06

Source: https://www.modelscope.cn/models/facebook/pixio-vitl16

---

# Model Card for Pixio

Pixio is a family of versatile self-supervised vision foundation models. Pixio produces competitive dense features by simple masked autoencoding (MAE) on 2B web-crawled images with minimal human curation.

Pixio enhances MAE pre-training framework by using a deeper decoder, masking at a larger granularity, and introducing additional class tokens.

## Model Details

As described in the [Pixio](https://arxiv.org/abs/2512.15715) paper, 5 models are provided:

- 1 ViT-5B trained from scratch,
- 4 ViT-B/L/H/1B models distilled from the ViT-5B

Each model takes an image as input and returns eight class tokens and patch tokens. These models follow a standard ViT architecture, with a patch size of 16. For a 256x256 image, this results in 8 class tokens + 256 patch tokens = 264 tokens.

The models can accept larger images provided the image shapes are multiples of the patch size (16).

### Model Description

- **Developed by:** FAIR at Meta, HKU
- **Model type:** Vision Transformer
- **License:** [FAIR Noncommercial Research License](https://github.com/facebookresearch/pixio?tab=License-1-ov-file#readme)

### Model Sources

- **Repository:** [https://github.com/facebookresearch/pixio](https://github.com/facebookresearch/pixio)
- **Paper:** [In Pursuit of Pixel Supervision for Visual Pre-training](https://arxiv.org/abs/2512.15715)

### How to use

Here is how to use this model:

```python
from transformers import AutoImageProcessor, AutoModel
from PIL import Image
import requests

url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
image = Image.open(requests.get(url, stream=True).raw)

model_id = "facebook/pixio-vitl16"
processor = AutoImageProcessor.from_pretrained(model_id, trust_remote_code=True)
model = AutoModel.from_pretrained(model_id, trust_remote_code=True)

inputs = processor(images=image, return_tensors="pt")
outputs = model(**inputs, output_hidden_states=True)
last_hidden_states_norm = outputs.last_hidden_state # 8 class tokens + patch tokens after last LayerNorm
last_hidden_states = outputs.hidden_states[-1] # 8 class tokens + patch tokens before last LayerNorm
```

## Citation

```
@article{pixio,
  title={In Pursuit of Pixel Supervision for Visual Pre-training},
  author={Yang, Lihe and Li, Shang-Wen and Li, Yang and Lei, Xinjie and Wang, Dong and Mohamed, Abdelrahman and Zhao, Hengshuang and Xu, Hu},
  journal={arXiv:2512.15715},
  year={2025}
}
```