VAR
by FoundationVision (organization)
[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! (description from the project’s GitHub page)
Repository facts
- Stars
- 8,757
- Forks
- 572
- Open issues and pull requests
- 62
- Primary language
- Jupyter Notebook
- License
- MIT License (MIT)
- Owner
- FoundationVision · Organization
- Created
- Apr 1, 2024
- Last push
- Nov 10, 2025
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 4,394: FoundationVision/Infinity
[CVPR 2025 Oral]Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis
1,593 starsPythonMITLast push Apr 16, 2026
Rank 3,267: buaacyw/MeshAnything
[ICLR 2025] From anything to mesh like human artists. Official impl. of "MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers"
2,305 starsPythonOther licenseLast push Apr 28, 2025
Rank 9,155: FoundationVision/UniTok
[NeurIPS 2025 Spotlight] A Unified Tokenizer for Visual Generation and Understanding
535 starsPythonMITLast push Nov 14, 2025
Rank 3,702: FoundationVision/LlamaGen
Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation
1,973 starsPythonMITLast push Aug 15, 2024
Rank 6,095: thu-ml/Causal-Forcing
[ICML 2026] Official codebase for "Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation" & Causal Forcing++
1,007 starsPythonApache-2.0Last push Oct 3, 2026
Rank 8,174: FoundationVision/Liquid
(Accepted by IJCV) Liquid: Language Models are Scalable and Unified Multi-modal Generators
640 starsPythonMITLast push Jun 1, 2026