Loading video...
Video Failed to Load
Florence-2, the new vision foundation model by Microsoft, can now run 100% locally in your browser on WebGPU, thanks to Transformers.js! 🤗🤯 It supports tasks like image captioning, optical character recognition, object detection, and many more! 😍 WOW! Demo (+ source code) 👇
88,762 views • 2 years ago •via X (Twitter)
9 Comments

Xenova2 years ago
ONNX models: Source code: Demo:

nickmystic2 years ago
amazing work!

Samuel Tallet2 years ago
It's awesome, thank you Xenova! Does the "Florence-2-large" model can also run on the client-side with WebGPU acceleration?

snats2 years ago
When is v3 coming out? I love this!

Aiflowly.com2 years ago
Amazing! We should add this to the list of our integrations.

Aaron Planell2 years ago
@daviddincognit Maybe this can be interesting for you

PDS_B2BMGMT2 years ago
I tried twice! I only got this

Thomas Hill2 years ago
🔥

Gather Grove2 years ago
This actually works great even on my lame GPU, but it's accuracy is kinda random. The next version will be awesome.
