Kevin Griffing PRO
AI & ML interests
Recent Activity
Organizations
kk i fixed the directory creation! i also added a bpm slider in the JerryUI since it won't have access to the bpm/tempo inside your Audacity project
https://github.com/betweentwomidnights/gary4juce/releases/tag/v2.0.0-standalone
just updated this same pre-release. i imagine going forward i should create a new one to match the new commits... still new to how github releases work in practice
First version of the PC standalone release just for you homie!
https://github.com/betweentwomidnights/gary4juce/releases/tag/v2.0.0-standalone
fingers crossed it works on your machine. your help testing is greatly appreciated.
I'd love for you to come hop in discord and yell at me if anything's going wrong or the app is confusing. https://discord.gg/VECkyXEnAd
couple edge cases and steps to make it prettier like a gr.Audio component but I should have it done shortly! are you on PC, Mac or Linux? (i will build the standalone for all of them but whichever you use I will test thoroughly first)
i have just realized the JUCE standalone app allows me to drag audio INTO audacity. I am now working on extended functionality so that instead of needing to 'press play' to record the input audio like ableton/fl studio users do, you will be able to drag audio from your system folders into the standalone plugin and get essentially all the functionality we enjoy!
thank you for the push to make this application work for even more people! hopefully after an all-nighter I will have a release of the standalone for you that makes sense for non-DAW users. I'll share updates here!
had never thought to try in audacity! technically...it does load lol... the problem is you can't record the audio into gary's buffer just by pressing play in Audacity. I guess the way plugins work in this program is real different than a DAW. I also can't seem to drag the audio from the plugin into audacity either because of the way it loads plugins...
I think I would have to reimagine the way the plugin works for it to make sense in this program :/ so many things to build so little time!
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.
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)
