Repository · GitHub

FoundationVision/VAR

[NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly yet state-of-the-art* codebase for autoregressive image generation!

View on GitHubReport an issue

Owner	FoundationVision
License (as declared)	MIT
Stars	8,753
Forks	572
Main language	Jupyter Notebook
Created	1 April 2024
Last updated at source	10 November 2025

jupyter notebookauto-regressive-modelautoregressive-modelsdiffusion-modelsgenerative-aigenerative-modelgptgpt-2image-generationlarge-language-modelsneuripstransformersvision-transformer

Embed this entry

<iframe src="https://silytics.si/embed/item/c98a3c82-f589-4d27-8a9c-bd0548624e7c" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Free, no tracking. More about feeds and embeds.

More from FoundationVision

ByteTrackRepository
LlamaGenRepository

Silytics shows public metadata from GitHub and links to the original. Information may be incomplete or out of date. Last refreshed 15 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.