Thanks for the video. I'm surprised I haven't really seen other OpenVino uploads from people playing with the Style Remix. I've been having fun experimenting with it for the past week. I look forward to see what it evolves into like we've seen with chat and image-generating ai...
Great observation, I think it's because Audacity doesn't jump into your mind when you think about Music Generation, maybe that will change over time. Also a lot of people on RUclips are there for the News, so not really using the tools for anything. More to come! I love messing with Audio projects and everyone wants image stuff it seems, so thanks for the feedback !!
i like your vibe, you try to have fun no matter what you do, and you have a curious mind that I like a lot, personally, I don't like 90% of modern music, a bit of an old soul I guess haha, I would love to find a way to create lo-fi or retro 70s 80s music locally, specially lo-fi
we will pivot to TTS and Speech generation again soon, it was planned to follow the animation packs. Kolors was a surprise, so a delay in my plans to accommodate it. watch this space !
it should immediately start processing after you enter in your remix prompt. try using CPU options to see if it work at all, but you should be ok with defaults.
yes, it can depend a lot on the settings/prompt for the remix and also the input sound, it will do strange things to fade in/ fade out / silence, because there is more to "denoise" and fill in. I had the benefit of playing with this a lot, so it can be unexpected. Also some words are better than others, i'm trying to find a good list.
It's a free horrible mess, people have to start somewhere, this is more of an open minded look at the integration of free generative AI features into Audacity. FLstudio also offers this, however that would be another video entirely ;)
![FLUX1 - Introducing my Passive Detailers [Part One]](http://i.ytimg.com/vi/QuCbu9wh47M/mqdefault.jpg)
![Jack Harlow - Hello Miss Johnson [Official Music Video]](http://i.ytimg.com/vi/Q86_nlRoIGw/mqdefault.jpg)
Thanks for the video. I'm surprised I haven't really seen other OpenVino uploads from people playing with the Style Remix. I've been having fun experimenting with it for the past week. I look forward to see what it evolves into like we've seen with chat and image-generating ai...
Great observation, I think it's because Audacity doesn't jump into your mind when you think about Music Generation, maybe that will change over time. Also a lot of people on RUclips are there for the News, so not really using the tools for anything.
More to come! I love messing with Audio projects and everyone wants image stuff it seems, so thanks for the feedback !!
Really awesome!! Does this require GPU vram?
you can choose all CPU if you want, as i explained and showed, you can select which operations and to use GPU or CPU. Speed is the only factor ;)
i like your vibe, you try to have fun no matter what you do, and you have a curious mind that I like a lot, personally, I don't like 90% of modern music, a bit of an old soul I guess haha, I would love to find a way to create lo-fi or retro 70s 80s music locally, specially lo-fi
"...just use any # that's familiar to you..." hahaha
you have a keen eye for details ! ;)
I would love to see your beat creation workflow... no need to be PRO.. as long as we have fun and enjoy creating weird stuff!!
Thanks, i was waiting to see if anyone was interested, so i'll make a longer video where we can look at a fuller process :D thanks for watching !
i need some vocal style replicator with custom text, is that possible? perhaps even on beat with a given instrumental we made like here? thanks boss
we will pivot to TTS and Speech generation again soon, it was planned to follow the animation packs. Kolors was a surprise, so a delay in my plans to accommodate it. watch this space !
I'm trying to use this model, but when I select Music Style Remix and then set it up nothing happens, what am I doing wrong?
it should immediately start processing after you enter in your remix prompt. try using CPU options to see if it work at all, but you should be ok with defaults.
I figured out: All i had to do was put all the options in CPU to get OpenVINO work. Oh, one last thing: Don't mind my english, i'm Italian.
...and thanks for your help.
69420. I like your style
It gives me strange results! 🙁
yes, it can depend a lot on the settings/prompt for the remix and also the input sound, it will do strange things to fade in/ fade out / silence, because there is more to "denoise" and fill in.
I had the benefit of playing with this a lot, so it can be unexpected. Also some words are better than others, i'm trying to find a good list.
What is that stupid horrible mess? :D :D For the moment that is a garbage product by all standards. There much better separation tools online.
It's a free horrible mess, people have to start somewhere, this is more of an open minded look at the integration of free generative AI features into Audacity.
FLstudio also offers this, however that would be another video entirely ;)
@@FiveBelowFiveUK i agree
uggly-horrible!!!!!
Yes, and extremely outdated, it's nice to see the difference over time :)