FoundationVision/UniTok

[NeurIPS 2025 Spotlight] A Unified Tokenizer for Visual Generation and Understanding

40
/ 100
Emerging

UniTok helps researchers and developers working with AI models that interpret and create images. It acts as a universal translator, converting visual data into a standardized digital format that AI models can understand, and vice-versa. This allows for a more efficient and accurate exchange of visual information between different AI systems, benefiting those building advanced visual AI applications.

517 stars.

Use this if you are developing AI models that need to both generate images from descriptions and understand what's in an image, and you want a unified approach for processing visual data.

Not ideal if your primary goal is simple image processing or if you are not working with advanced multimodal AI systems.

visual-AI-development image-generation image-understanding multimodal-AI computer-vision-research
No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

517

Forks

11

Language

Python

License

MIT

Last pushed

Nov 14, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/FoundationVision/UniTok"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.