UDIO - Make Music From Text Prompts
HTML-код
- Опубликовано: 11 апр 2024
- UDIO vs SUNO - here we go! Generating music from text has never been easier, and boy is this a lot of fun :) Enter your own lyrics, use AI generated ones, extend, remix and more!
No install!
Want to support the channel?
/ nerdyrodent
Link:
www.udio.com/
== More Stable Diffusion Stuff! ==
* Installing Anaconda for MS Windows Beginners - • Anaconda - Python Inst...
* Installing ComfyUI - • How to Install ComfyUI...
* Faster Stable Diffusions with the LCM LoRA - • LCM LoRA = Speedy Stab...
* Make an Animated, Talking Avatar - • Create your own animat...
* One Image Gets You a Consistent Character in ANY pose - • Reposer = Consistent S... - Наука
That song at the end though 🤣
will soon be in the hit parade
Suno is so much fun. I can't wait till we have this kind of stuff locally
Then running in realtime, then with neurofeedback for optimal yass factor
We can train our own music models with Stable Audio weights but it does not do vocals yet.
@@digidope Oh can you share more information/links for us here for this? :):):)
The song at the end was really nice.
LOL! The first song mix with english and chinese gave me a surreal experience... amzing!
The outro is brilliant ! Made my day! :)
I tried this last night and was impressed, it sounded much clearer and more usable than Suno. The way you build and extend a song was very easy to use too. I get that they don't want to copy proper artists but I was slightly disappointed that you couldn't prompt for 'in the style of....' followed by an artists name to get a similar style. It's still great though.
Had to try it out, instant addiction.. a little unstable at this point, but this is gonna be a toy of the future!
This reminds me of Jukedeck. One of the first AI music generators.
This is the coolest thing ever
The quality of the output is amazing and I'd love to hear more about how it functions under the hood, but i find it frustrating in the same way that early image generators were. There's just not enough controllability. If you want something specific, you'll never get it. Without it being open source, I don't expect it to get the same kind of controlnet and lora goodness that made stable diffusion so useful. Particularly, I want to upload my own simple melodies and get variations or different styles, but also more fine grained control over the style, tempo, instruments, voice etc.
I had fun making this, nice piece of ai
Oh man I'm going to use this hardcore :D sweet! :D
🦞
@@NerdyRodent I think I broke it already, a number of songs have errors and back processing errors - I wanted to extend a song but I don't think that worked?
IDK I got two good mini-songs from it that I'm happy with but I want the full songs!
This is pretty insane and amazing though!
@@DeconvertedMan The server may be pretty loaded right now, but extend is working for me!
@@NerdyRodent oh. hmm I guess I did it wrong then. Things are just not working will have to try back latter. :D
10 songs for free daily is hella enough for most free users tbh! As you're dealing with a competitor to song A.I, and what better way to make customers than a free tier, with more than 10 songs daily for a smol coin
This is great. Do you think there will be an open source equivalent where you will be able to train your own models?
Given time, for sure!
Needless to say, I find more synthetic music such as synthwave and eurobeat to be indistinguishable from the real thing. As for classical music, 5 minutes seems to be about the absolute limit you can go to still produce a fairly coherent piece. I haven't managed to get Udio to produce classical ballet music - it always drifts off into some kind of Brucknerian symphonic style.
We need a local webui that can do even 60% of what Suno/Udio makes, then we are golden!
And with a decent license too!
@@NerdyRodent this! If I cant use these songs commercially, it's nothing more than a fun gimmick.
oh my god, that is epic, good nerdy rodent song hahahah XDD
I wonder if there’s some open source audio music generator to run locally
Outro "inspired by Scooter"
That last song got my sub 😂😂
Is there a local version of this?
Can we post these to spotify? Would spotify ban the account? Also is there an ai cartoon video generator?
is there a way to do it locally?
Yeah, they have a thing called MAGNet that does this locally, though, I guess its quality is comparable to Stable Diffusion 1.5 untuned.
As for Udio, no, it's online only.
I enjoyed it more when you used to sing in the bath
😉
THIS IS EPIC, THE SERVERS ARE SLOW ITS BACKED UP HAMMERING IT SO MUCH LOLLOL1
Not local? D:
I'm so upset that I can't find a local open source version of this...
Give it a year or so…
Theme songs for every RUclips channel now. Surprised you didn't create a ComfyUI rap. A good use case would be to learn languages great for repetition since you can use LLMs to crank out the lyrics of vocab you do not know.
I worked with Udio all night, and it's incredible. Especially for creating music for video and RUclips "soundtracks".
Stems are coming.
Yay!
An ad?
i thought udio is audio without a A but now i am unsure xD
Udio is hundreds times better than Suno. I just wish we can find a way to own the songs we make. I've only been playing with it a week and I think making Ai songs has become my past time hobby. I've been trying to mix genres to get a unique beat and sound and I can say I'm halfway there. Although I think it's great at the moment, I don't think it will be like this forever. Eventually, they'll be a reason to stop using it, whether it's copyright, pay plan, or limitations.
Thanks for sharing, but I much prefer projects that we can run locally!
Same here!
Will.i.am did it
English is censored but in other languages it seems to do anything 😂
Wrong.
could be STUdio, could be AUdio, either way it's pronounced YOUdio
Music Copyright made this possible, now due to their greed they can go to hell and out of business as people are forced to make their own songs to use in their personal videos, no one will care about some media hyped up garbage you need to pay for from now on.
That's not music, is it? Just a noise...
Well yeah music is noise lol