How to select models in Multi-AI Ensemble for best processing results

[djkcyl]

This is my current option, but I find that the audio quality after processing and merging is not as good as the audio quality of these different models when processed separately

So I want to know how these models should be matched to maximize the quality in the usual songs

[Anjok07]

The key is to find the ensemble that works best for the tracks being processed. It's hard to recommend a best ensemble overall. Personally, I don't ensemble with more than 2 models unless I really need to.

Check out the new update! New ensembling options have been added.

[djkcyl]

okey, thx

[thenormal]

This is my current option, but I find that the audio quality after processing and merging is not as good as the audio quality of these different models when processed separately

So I want to know how these models should be matched to maximize the quality in the usual songs

Demucs v3 (md_extra model) seems to provide the best results. Sometimes, however, the vocals are not properly processed with it. When that happens, I use Multi-AI Ensemble mode with the following settings for better vocals extraction: