OmniTokenizer
[NeurIPS 2024]OmniTokenizer: one model and one weight for image-video joint tokenization.
Use a single model to process both images and videos for generating visual content, improving efficiency in media projects.
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytime[NeurIPS 2024]OmniTokenizer: one model and one weight for image-video joint tokenization.
OmniTokenizer has 325 stars on GitHub. It has been forked 8 times. OmniTokenizer is written mainly in Python. It has been in active development since 2024. OmniTokenizer is available under the MIT license. Its main topics are auto-regressive-model, image-generation, tokenization, vae.
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.
What license does OmniTokenizer use?
OmniTokenizer is available under the MIT license.
What language is OmniTokenizer written in?
OmniTokenizer is written mainly in Python.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/foundationvision-omnitokenizer.html)
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.