Microsoft silently updated OmniParser on the hub 👀 60% faster than v1 - sub-second latency on a 4090! "OmniParser is a general screen parsing tool, which interprets/converts UI screenshot to structured format, to improve existing LLM based UI agent." Bonus: you can try it out for free!

Model checkpoint:

Try out the model for free here:

Our speech-to-text models are the most accurate on the market with top rankings across industry benchmarks. - The highest accuracy rates—up to 95% - Up to 30% fewer hallucinations than other leaders - Low latency—63 minutes converts in 35 seconds Try via API for free today 👇

Super hard to use omnitool and its very slow even on my 4080. Like taking 1min+ just for the Image parsing.

are you using the GPU, could be that you're running the op via CPU

The problem is u need huge gpu till run it

Setup is a nightmare on Windows. The setup is: FUSE-based (horribly slow) Assumes Linux KVM is present (Not true on Windows) Not built with Windows users in mind (requiring modifications to scripts) The devs need to release a setup procedure optimised for Windows.

This is really interesting

@huggingface @huggingface, incredible improvements with OmniParser. Speed like this can truly enhance workflows and drive productivity. 🚀 #Innovation

That's impressive progress. Faster parsing opens up so many possibilities for UI agents

such a project, want to build some code samples with this.