Hugging Face's logo

MiniMaxAI
/
MiniMax-Music3

Text-to-Audio
Diffusers
Safetensors
PyTorch
minimax_music3
music-generation
text-to-music
sglang-omni
Model card Files
xet
 Community
19

Any plans to release a RVQ encoder or Flow-VAE encoder to enable audio-conditioned generation?

#11
by TheLatentSpacer - opened
Discussion
TheLatentSpacer

Thanks for publishing these weights, the quality is great.

I'm wondering whether reference-audio conditioning (continuation, style priming, repaint, etc.) is possible with the released weights? As far as I can tell it isn't, because no audio-to-latent or audio-to-token path was published

Any plans to release any of these paths to enable audio-conditioned generation?

Thanks either way!
bghira
This comment has been hidden (marked as Resolved)
bghira

here's an open reproduction of a compatible RVQ encoder https://huggingface.co/collections/SimpleTuner/open-rvq-encoder-for-minimax-music-3

i'm interesed to see what you do with it and how you enable audio-conditioned generation.

Sign up or log in to comment