OmniTokenizer
by FoundationVision · GitHub
[NeurIPS 2024]OmniTokenizer: one model and one weight for image-video joint tokenization.
⭐ Stars
325
🍴 Forks
8
📜 License
MIT
Commercial use OK📅 Created
2024
🔄 Last commit
2 yr ago
🏷️ Category
auto-regressive-model
💻 Language
You maintain this project?
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
📈 Star history
2026-07-202026-07-21
📄 About
[NeurIPS 2024]OmniTokenizer: one model and one weight for image-video joint tokenization.
❓ Frequently asked questions
What is OmniTokenizer?
[NeurIPS 2024]OmniTokenizer: one model and one weight for image-video joint tokenization.
Is OmniTokenizer open source?
OmniTokenizer is an open-source project. It is released under the MIT license.
Is OmniTokenizer free?
Yes. OmniTokenizer is free and open source — you can use, modify and self-host it.
🏅 Maintainer of this project?
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://opensourceai.tech/project/foundationvision-omnitokenizer.html)
🧬 Related projects🧬 View the DNA map →
VAR
[NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Offi…
★ 8.7k · auto-regressive-model
MeshAnything
[ICLR 2025] From anything to mesh like human artists. Official impl. of "MeshAnything: Artist-C…
★ 2.3k · 3d
LlamaGen
Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation
★ 2k · auto-regressive-model