[GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction"

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

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.

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".

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

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

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

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}
}