VAR
FoundationVision/VAR
[NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeli
[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!
Categories
Tags
Similar tools
transformers
huggingface/transformers
huggingface/transformers
rtk
rtk-ai/rtk
CLI proxy reducing LLM token consumption
hello-agents
datawhalechina/hello-agents
《从零开始构建智能体》——从零开始的智能体原理与实践教程
worldmonitor
koala73/worldmonitor
Real-time global intelligence dashboard
TrendRadar
sansan0/TrendRadar
告别信息过载，你的AI舆情监控助手与热点筛选工具
daily_stock_analysis
ZhuLinsen/daily_stock_analysis
LLM-driven multi-market stock analysis system with comprehensive market data, real-time news, decision dashboard and automated notifications.
Install
git clone https://github.com/FoundationVision/VARREADME
VAR: a new visual generation method elevates GPT-style models beyond diffusion🚀 & Scaling laws observed📈
Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction
NeurIPS 2024 Best Paper
News
- 2025-11: We Release our Text-to-Video generation model InfinityStar based on VAR & Infinity, please check Infinity⭐️.
- 2025-11: 🎉 InfinityStar is accepted as NeurIPS 2025 Oral.
- 2025-04: 🎉 Infinity is accepted as CVPR 2025 Oral.
- 2024-12: 🏆 VAR received NeurIPS 2024 Best Paper Award.
- 2024-12: 🔥 We Release our Text-to-Image research based on VAR, please check Infinity.
- 2024-09: VAR is accepted as NeurIPS 2024 Oral Presentation.
- 2024-04: Visual AutoRegressive modeling is released.
🕹️ 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 provide a demo website for you to play with VAR Text-to-Image 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 
| model | reso. | FID | rel. cost | #params | HF weights🤗 |
|---|---|---|---|---|---|
| VAR-d16 | 256 | 3.55 | 0.4 | 310M | [var_d16.pth](https://huggingface.co/FoundationVision/va |