Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
Back to feed
thecollabagepatch 
posted an update 6 days ago
Post
359
hey musicians

hf continues to make the anti-suno device possible with gary4juce, the VST for your DAW that doesn't try to replace you.

v2 just released. https://thepatch.gumroad.com/l/gary4juce (pay what you want)

now you can use google's magenta-realtime model to generate 48k samples based on your input audio (or other model outputs...there's 4 to play with now).

just duplicate my hf space, turn on an L4/L40s and throw the url into the plugin.

i've got a few finetunes you can switch to as well. or you can push your finetune to the hub and play around.

the space: thecollabagepatch/magenta-retry (you can also use the html web tester to play around with realtime generation on the L40s)
karenny

cool!

asigalov61

@thecollabagepatch Great job! But magenta-realtime kinda sucks IMHO. Can you make the same thing for stable-audio or FB musicgen?

Thank you.

·
thecollabagepatch
•
edited 3 days ago

musicgen, stable-audio-open-small and melodyflow are all part of the VST as well :) I focus on input audio wth musicgen and melodyflow.

The backend for stable audio, musicgen and melodyflow can be spun up locally using a docker-compose network in my github or you could also use the one-click installer i provide in the gumroad.

repo here: https://github.com/betweentwomidnights/gary-localhost-installer

I can certainly make the docker containers I created for them run on hf infrastructure as well... i provide a remote backend free of charge for those models for mac users and those without a gpu.

In this post