KobiMusic DEMO
A downloadable tool for Windows
This is a demo for KobiMusic, you can find the paid version here. In this version you cannot save your creations and your sessions are limited to 3 minutes
Note that the newest version has many bug fixes, a better model, and more features.
Samples
Do note that I cherry picked these samples and I went back and regenerated, however, we did not place down a single note for the results (we truncated some of the results though).
From scratch
Continuation of the C Major scale (AI at 4 seconds)
You can also look at the KobiMusic youtube channel for more music
Download
Install instructions
Thanks for downloading the demo! For windows users there is an exe named "main.exe", which you run. For linux users, the file should be in the root of the folder (I would also recommend for linux users to execute the file from the terminal because on linux it takes a while to open)
Development log
- New KobiMusic update makes its way into the demoDec 03, 2023
- Updated demoOct 10, 2023
Comments
Log in with itch.io to leave a comment.
i keep getting these errors and have idea how to fix it
(it also bots me out of the program after)
fluidsynth: error: no MIDI in devices found
. renaissance |
The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.
Setting `pad_token_id` to `eos_token_id`:50256 for open-end generation.
WARNING:tensorflow:AutoGraph is not available in this environment: functions lack code information. This is typical of some environments like the interactive Python shell. See https://github.com/tensorflow/tensorflow/blob/master/tensorflow/python/autograph... for more information.
69.4
Hmm... to be honest i got no clue, can you possibly send me your computer's specs?
my processor is a Intel(R) Core(TM) i5-8400 CPU @ 2.80GHz 2.81 GHz, my gpu is a NVIDIA GeForce RTX 2060, and i have 16 GB of ram, let me know if you need other info
Ok, you are definitely above the requirements, and it looks like it actually does generate something before crashing, meaning its probably an issue with the handling after it generates. If it crashes before you switch tabs to look at the generation, it could maybe be an error with your drivers potentially. If it happens after you switch tabs, it may be due to drivers aswell potentially. Try using a different model to generate and if that doesn't work, idk. Also you may want to close out of any other windows incase you had them open before
Hey there, i want to ask you, what is the best small model from the list? I don't get the difference between the different Musenet models
Openmusenet-2.11-L is basically an early version of the large size models, so it is not a small model
Openmusenet-2.11-M is the largest of the medium models, then Openmusenet-2.11-S is a smaller version, Openmusenet-2.11-3M is kinda a joke version, so i would probably recommend Openmusenet-2.11-M since its about 1/3 the size of the larger models and is still a somewhat reasonable quality (the first video in the samples is by it)
Hi! Whenever I try to open the program, I'm met by a very quick flash of this error but then it closes out. Any help is appreciated, I'd love to use this!
I haven't touched anything and I don't know how to fix it myself, so I'm coming here. I'll update if I figure anything out before you get back to me!
I think i've found the error (for some reason, i forgot to include the fluidsynth dll when building)! So try re-downloading it and it should (in theory) work. Seriously thank you for telling me this lmao i dont know how i didnt find this sooner
Thanks
This error means you ran out of vram while generating/loading the model. So try closing out of other windows or try loading a smaller model like openmusenet-M or openmusenet-s
alright i sort of got it to work with the smaller models. is there a way for me to run the larger model.
i was also trying to see if there was a way to generate more than 4 bars or material but i couldnt find an option for that.
lastely is there something i can do about these errors
thanks
These messages are intentional, currently, there is no way to run the larger models with your gpu. The amount of notes the ai generates is automatically set to the max so it is not possible to generate more than the max
ok, am i only allowed to look at one generation on the demo version? when i switch generations and then press play nothing plays.
You should be able to see/play multiple, you can move the red cursor with the right mouse button and cursor, and play/stop is in the bottom left
On vacation btw will be back like the 21st so i cant update rn if you have issues within this timeframe
doesn't run win11 latest py
bruhhhhhhhh you gotta be kidding me
Can you send a screenshot or tell me what happens please?
It was just open and closing.
I got it to run.
Then froze at generation.
Then generated over 100% -xx seconds. Nothing really seems to have happened though.
It also says
fluidsynth: error: no MIDI in devices found
!There seems so be no Cuda (GPU) on your device.. Generation may take a minute
The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.
Setting `pad_token_id` to `eos_token_id`:50256 for open-end generation.
('Bad header in MIDI file.', b'\xff\xfb\x90d')
This error occurs because you are trying to open a midi 0 file, which is (currently) unsupported. You need to convert the file first to midi 1 in order for it to work. I would recommend opening it in https://signal.vercel.app/edit then saving it via file > save and it should automatically convert it, so you should be able to open the new file then.
ohh ok. Generation probably did not freeze but if you don't have a gpu it will take like forever to generate (5 minutes probably for large model), which is longer than the duration of the demo. after 3 minutes the demo will close out. if you still want to still try the demo i would recommend going with a smaller model like the medium or small model.
That is a bit strange though for the fluidsynth error... Are you able to hear the notes when you play?
Could you perhaps add an updated demo version for a more indicative representation of the functionality? I mean, I have like, no money and i'm very tempted to get this...but...
Anyway, it looks pretty cool. But in the world of sound/music, there's so much crap, saturation, essentially clones, etc that I have to be rather picky and discerning.
Yeah sure, sorry lol, I've been procrastinating updating the demo but I'l actually try to get around to updating this
Cheers dude, I didn't mean to suggest you should do that right now or whatever...just, it's probably good for potential customers.
Its now been updated btw.
Okay, so I downloaded, installed and attempted to run. I figured something like this'd happen. Run main.exe, python error, FormatMessageW, loadlibrary failed crap, probably because I'm running Windows 7. I dunno.
Anyway, cheers.
Yup thats probably it sadly, windows 7 hasnt been supported in a while now so i think the newer versions of python dropped support for it. I think i recently upgraded to the latest python.