# var

**Repository Path**: hf-models/var

## Basic Information

- **Project Name**: var
- **Description**: Var 是一个通用的预训练模型，用于处理多种自然语言处理和文本生成任务，具有良好的效果。
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2024-04-10
- **Last Updated**: 2024-06-09

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

---
license: mit
datasets:
- imagenet-1k
language:
- en
- zh
---




# Model Card for VAR (Visual AutoRegressive) Transformers 🔥

<!-- Provide a quick summary of what the model is/does. -->

[![arXiv](https://img.shields.io/badge/arXiv%20papr-2404.02905-b31b1b.svg)](https://arxiv.org/abs/2404.02905)[![demo platform](https://img.shields.io/badge/Play%20with%20VAR%21-VAR%20demo%20platform-lightblue)](https://var.vision/demo)

VAR is a new visual generation framework that makes GPT-style models surpass diffusion models **for the first time**🚀, and exhibits clear power-law Scaling Laws📈 like large language models (LLMs).

<p align="center">
<img src="https://cdn-uploads.huggingface.co/production/uploads/60e73ffd06ad9ae5bbcfc52c/FusWBHW8uJgYWO02HFNGz.png" width=93%>
<p>
  
VAR redefines the autoregressive learning on images as coarse-to-fine "next-scale prediction" or "next-resolution prediction", diverging from the standard raster-scan "next-token prediction".

<p align="center">
<img src="https://github.com/FoundationVision/VAR/assets/39692511/3e12655c-37dc-4528-b923-ec6c4cfef178" width=93%>
<p>


This repo is used for hosting VAR's checkpoints.

For more details or tutorials see https://github.com/FoundationVision/VAR.