Performance comparison

by felfri - opened 10 days ago

Discussion

felfri

10 days ago

Thanks for the great release. How does this model perform compared to its predecessor, rmbg-1.4?

MishaF

BRIA AI org 9 days ago

Hey @felfri - as you can see in the model card, the new version outperforms the old one significantly.
Over our benchmark, 2.0 gets over 90% success vs less than 74% for 1.4

tdurbor

about 10 hours ago

Hello ! Thanks for the release, I'm curious about the dataset on which you benchmarked the model. What are the characteristics of the dataset and the methodology you used to do the benchmark?

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment