Hugging Face's logo

ONE-Lab
/
GUI-Vid

Video-Text-to-Text
English
gui
agent
Model card Files Community
2

This is the first VideoLLM with powerful GUI-oriented capabilities, retrained on GUI-World.

It was presented in GUI-WORLD: A Dataset for GUI-oriented Multimodal LLM-based Agents.

See Github for how to use GUI-Vid for GUI understanding tasks.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
Video-Text-to-Text
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Dataset used to train ONE-Lab/GUI-Vid

Collection including ONE-Lab/GUI-Vid