[HN Gopher] Music ControlNet: Multiple Time-Varying Controls for...
___________________________________________________________________
Music ControlNet: Multiple Time-Varying Controls for Music
Generation
Author : GaggiX
Score : 35 points
Date : 2023-11-14 19:27 UTC (3 hours ago)
(HTM) web link (musiccontrolnet.github.io)
(TXT) w3m dump (musiccontrolnet.github.io)
| GaggiX wrote:
| The model used here is very small, 41M, I wonder how well it
| would scale at a bigger size.
| TaylorAlexander wrote:
| I was thinking recently, now that we have multimodal text and
| image models, music and sound generation will probably get rolled
| in to the big foundation models. And then we can look at adding
| more niche modalities like 3D model generation. As we begin to
| explore large numbers of modalities we will have highly
| generalized models.
| bongwater_OS wrote:
| Love seeing the MIR research from CMU recently. Chris Donahue is
| the man!!
| brrrrrm wrote:
| can I try this out somewhere?
| SpaceManNabs wrote:
| I understand that this paper is about controls. I wish there was
| more detail in how it differs to other music generation methods
| like MusicLM. That seems to be in the MusicGen paper though [5]!
|
| But then I am more curious about how this compares to MusicLM in
| terms of music generation.
___________________________________________________________________
(page generated 2023-11-14 23:00 UTC)