Hugging Face's logo

stabilityai
/
stable-audio-open-1.0

Text-to-Audio
Stable Audio Tools
Diffusers
Safetensors
English
Model card Files
xet
 Community
59

What do you use this model for?

#17
by the-french-artist - opened
Discussion
the-french-artist

Given the 47s limit, what are you currently experimenting on?

I have tried some ambiance sounds, some loop samples, and other random noises.
Is there a small audio category I am missing ?

victor9000

generating audio samples to use in producing a larger arrangement
annieone

Strictly for scientific purposes xD (caution: NSFW)
deleted

Any way to extend the time limitation to something useful? I agree with the OP. 47 seconds is pretty low.
ameerazam08

@Nurb4000
Already mention in paper and if wanted to increase then make change in pipe

deleted

@Nurb4000
Already mention in paper and if wanted to increase then make change in pipe

tks ill go looking for that. Just now ran across it, not had time to read a lot, just the overviews . but if it wasn't doable at all, figured id not bother.

the-french-artist

@annieone
"We do what we must because we can"

I was totally expecting that kind of answer, lets just hope the model doesn't get pulled because of you!

Sign up or log in to comment