Which icon is better?

We have three news.
1. We've added two models:
🎄 Mel-RoFormer by becruily (Instrumental)
🎄 De-reverb & De-echo by Sucial v2
2. De-reverb and de-ec...
2024-12-31 07:17:05 +0000 UTC View PostThe Mel-RoFormer model by unwa v2 has just been added! We're asking you to test it out and vote.
2024-11-05 08:27:01 +0000 UTC View PostA new model for strings/violins isolation has been added! 🎻🎻🎻
2024-06-10 11:12:21 +0000 UTC View PostAdded a new Mel-Roformer model for lead vocal isolation.
Compared to the previous ones it produces better results on some songs.
2024-05-16 09:57:30 +0000 UTC View PostA new model has been added to remove vocals. Unlike the BS-Roformer, the new model produces less muddy instrumentals.
2024-04-26 01:13:00 +0000 UTC View PostBS-RoFormer has just been added to the X-Minus / UVR Online!
This is a HQ model for music and vocal separation.
Many thanks to viperx for model training.
2024-03-27 13:23:48 +0000 UTC View Post
Thank you for your subscription! To start using Premium, please open the link and create an account if you don't already have one:
Thank you for your subscription!
To start using Premium, please open the link and create an account if you don't already have one:
Thank you for your subscription! To start using Premium, please open the link and create an account if you don't already have one:
Thank you for your subscription! To start using Premium, please open the link and create an account if you don't already have one:
If you are a new subscriber, please ignore this message. If you were subscribed to our Patreon in 2022 or earlier, please note that automatic charges will continue as of April 1, 2024 2024-02-21 23:42:56 +0000 UTC View Post
Hello! We'd like to let you know that Patreon has begun charging funds today for unknown reasons.
If you have had a charge, please let us know and we will refund your money. After that,
Hello everybody! Here's a Premium version that includes the new MDX models. Thanks to Anjok07 for model assistance, including computing resources for training.
Your secret link: ...
2021-12-18 08:39:15 +0000 UTC View PostHello everybody! Here are the new high-performance model. Thanks to Anjok07 for model assistance, including computing resources for training.
This is another model that sometimes handles echoes and reverb better than others. Unlike all the previous ones, it does not work with the Left-Right channels, but with the Mid-Side channels.
This is a new model that does better when other models fail. This model has a cutoff of 20,500 Hz. Enjoy!
2021-04-09 09:51:35 +0000 UTC View Post