FoundationVision/VAR
Visual Autoregressive (VAR) model generates images using GPT-style next-scale prediction, achieving state-of-the-art results and demonstrating scaling laws in visual generation.
Not currently ranked — collecting fresh signals.
star history
VAR reimagines image generation as a next-scale prediction task rather than next-token prediction, enabling GPT-style transformers to compete with and surpass diffusion models. The official implementation provides training and inference code for autoregressive image generation across multiple model sizes. It won NeurIPS 2024 Best Paper Award for demonstrating scaling laws in visual generation comparable to language model scaling.
Frequently asked
- What is FoundationVision/VAR?
- Visual Autoregressive (VAR) model generates images using GPT-style next-scale prediction, achieving state-of-the-art results and demonstrating scaling laws in visual generation.
- Is VAR open source?
- Yes — FoundationVision/VAR is open source, released under the MIT license.
- What language is VAR written in?
- FoundationVision/VAR is primarily written in Jupyter Notebook.
- How popular is VAR?
- FoundationVision/VAR has 8.7k stars on GitHub.
- Where can I find VAR?
- FoundationVision/VAR is on GitHub at https://github.com/FoundationVision/VAR.