VAR: a new visual generation method elevates GPT-style models beyond diffusion🚀 & Scaling laws observed📈

This is the official PyTorch implementation of Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction.

🕹️ Try and Play with VAR!

We provide a demo website for you to play with VAR models and generate images interactively. Enjoy the fun of visual autoregressive modeling!

We also provide demo_sample.ipynb for you to see more technical details about VAR.

What's New?

🔥 Introducing VAR: a new paradigm in autoregressive visual generation✨:

Visual Autoregressive Modeling (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".

🔥 For the first time, GPT-style autoregressive models surpass diffusion models🚀:

🔥 Discovering power-law Scaling Laws in VAR transformers📈:

🔥 Zero-shot generalizability🛠️:

For a deep dive into our analyses, discussions, and evaluations, check out our paper.

VAR zoo

We provide VAR models for you to play with, which are on or can be downloaded from the following links:

model	reso.	FID	rel. cost	#params	HF weights🤗
VAR-d16	256	3.55	0.4	310M	var_d16.pth
VAR-d20	256	2.95	0.5	600M	var_d20.pth
VAR-d24	256	2.33	0.6	1.0B	var_d24.pth
VAR-d30	256	1.97	1	2.0B	var_d30.pth
VAR-d30-re	256	1.80	1	2.0B	var_d30.pth

You can load these models to generate images via the codes in demo_sample.ipynb. Note: you need to download vae_ch160v4096z32.pth first.

Installation

License

This project is licensed under the MIT License - see the LICENSE file for details.

Citation

If our work assists your research, feel free to give us a star ⭐ or cite us using:

@Article{VAR,
      title={Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction}, 
      author={Keyu Tian and Yi Jiang and Zehuan Yuan and Bingyue Peng and Liwei Wang},
      year={2024},
      eprint={2404.02905},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

ifsheldon/VAR