Jupyter Notebook · MIT
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!
★ 8.8k
Stars
574 forks · 62 open issues
+3.0/wk
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
14.4
Momentum / 100
see the breakdown below
2y ago
Created
last push 12mo ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 3.0 | +3.0/wk, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | last week ran 0.46× the monthly pace |
| Freshness | 15 | 0.0 | last push 12mo ago; decays to zero at 180 days |
| Scale | 15 | 11.4 | 8.8k stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 14.4 | sum of the above |
Detail
| Topics | auto-regressive-modelautoregressive-modelsdiffusion-modelsgenerative-aigenerative-modelgptgpt-2image-generationlarge-language-modelsneuripstransformersvision-transformer |
| Matched on | LLM & Inference (large-language-models) |
| Short window | +3 stars over 7 days = 0.4/day |
| Long window | +24 stars over 26 days = 0.9/day |
| Lifetime average | 9.25 stars/day over 948 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |