what’s the most favorite? is it the “are you okay matt?” thread?
The matt thread is really funny though, i just didnt have much involvment.
“This has got to be my second favorite thread on this forum.” ~ SlavaCat
You have good taste.
Ultimately, at least to me, using Vital in the bigger picture is small potatoes, but once in awhile when I have the time, I don’t mind picking up a pea beside my small potatoes, loading it in my pea-shooter and firing it off. Even if it takes more than a few edits (launches).
Matt popping into maybe that thread you mentioned (the ‘Matt’ thread?) and saying something about the thread not being productive and as a result him locking it was kind of funny/cute.
My imagination for fun for that was like some of us as kids arguing in a home garage about a go-cart he made, and he pulls into the driveway after work and tells us that we’re not being productive and to go and get cleaned up and ready for supper and he’s going to close and lock the garage.
Thanks for your coding by the way.
1 Like
Yup circular seems to know what they’re talking about, mighty interesting!
i wish i didn’t need to sign in to download it. can’t remember the password i use for the account i use for these kind of things. i guess that’s a necessary speed bump to stop bots from eating bandwidth though. guess i’m a bot. (how could i even know for sure?)
The link fails in both Chromium-based browsers like Opera and Edge. Same problem with Firefox.
Works fine for me?
There’s chatter that this software doesn’t really do anything. could it be some kind of hype thing to indirectly raise capital to either create such a program or to not ever really build it? Allegedly it just downloads torch and there’s a few wavetables that are shuffled around to create the illusion that something has been done. Read that on bedroomproducersblog I think.
Got a source link for that bedroomproducersblog article/etc?
From my brief exploration of it; seems to do things; and from what I see/hear of others using it on the discord, also definitely seems like it’s more than what you’re describing it as.
Curious why so many people here seem to be so interested in spreading FUD.
I primarily use a custom guitar controller, and even playing live, I’m attacked by racist, misogynistic, homophobic POS claiming I’m not really playing because I use a computer, Arturia MiniFUSE, MIDI switches, MIDI expression pedals, and an HX Stomp.
I try to stay on top of advances in technology, but have to step carefully within the rock and experimental music world, since I’m not a young, cute, CisHet white woman. Guys use any excuse to tear me down, and anything that remotely looks like digital technology is a sign of no talent when I use it, but “genius” when white men use the exact same tech.
1 Like
for the record, i was initially blown away by the idea of this software, so I’m not anti tech, but i can’t rule out the potential of it being snake oil.
EpicToasty
This tool doesn’t do that. I’d actually respect a tool that could recognize the effects and wave shapes in a synth sample, but this doesn’t do that.
If you watch the original video, you’lll see that on the 4th preset supposedly generated, he pulls up vital without actually loading the preset, which means that the Vital instance already had the preset loaded before he used the app to generate it, which is impossible. Unless the entire video is staged and he’s a scammer farming excited people with a staged video and software that doesn’t do what he says.
Don’t believe me? Search the app’s folder for “wav” and watch one of the five results be a vital preset with everything already configured, that just so happens to match every result that occurs in both the video and every test I’ve tried with the software.
and
EpicToasty
I am so frustrated with all of the people telling me that my personal experience with this software not working is “just a bug lol”. I’ve tried this with samples that are short, and samples that are 4-8 minutes long. I’ve tried this on samples I’ve made, on pro sample pack samples I own, and even on samples made by presets that this software generates.
It never works. It never sounds remotely close to what I input. It takes the same amount of time processing a 1 mb wav file as it does a 60+ mb render of a song I made. The result is always the same two wavetables, with the same effects, with the same modulation routing. Every time.
If you look at the video, you’ll see that he forgets to actually load the preset into vital on the 4th or 5th preset. He just pulls up vital with the preset already loaded. Which is impossible because that means he loaded the preset BEFORE it had been “generated”. That means he staged and faked at least that part of the video. Deceptive.
If you try it yourself, go ahead and look at the various python scripts. Look at generator.py and explain why it uses code to generate RANDOM parameter values if it’s actually analyzing the sound files you put it.
Search “wav” in the install directory. You’ll find the default vital preset file that it renames and shuffles the parameters on.
Try to input a wav file with “.WAV” extension vs “.wav”. It errors out, meaning that somehow a developer that supposedly knows how to use PyTorch to employ AI software features failed to handle text case correction anywhere in their code. And that also means that it can’t tell that a file is a wav file by nature of the data it holds, it instead uses the the case of the file extension to do so. That suggests that the code isn’t even looking at the contents of the wav file.
I was so excited when I downloaded this software, and now that I’ve tried it so much and flooded my Vital with these multiple presets that are all just copies of the same basic preset hidden inside of it… I feel so deceived, cheated of my time, my attention, and my hype for AI development.
I’m so sick of all this hype from people who haven’t tried the software at all, and I know I can’t be alone in feeling misled and cheated. I feel really sorry for all the people who donated to the patreon after watching that staged video.
I’ll debate AI in music up and down, all day, I will. To the best of my knowledge, this isn’t real, and if it is, this AI is being exploited by a deceptive developer that grossly misrepresents what’s actually happening with this software.
that guy sounds pretty salty but there’s other comments on that page that align with his general sentiments.
2 Likes
Thanks for the link/comments. Yeah, they do sound pretty salty.
I’m not sure if they were just using the original version, or if they have joined the Discord and tried out any of the beta versions / improved models they have released since (including macOS builds).
Obviously this is only my personal view, but if it were snake oil, there seem to be a decent number of fake puppet accounts on their discord that act remarkably like real humans that very much give me the impression that it’s just an early stage tool being developed and iterated on as they go. And also, the devs would be wasting a lot of time engaging with their community to get feedback/on features/improvements/etc as well. And that’s by me doing nothing more than joining a free discord server; didn’t have to pay anything to a patreon/etc.
At the end of the day, trolls on the internet gonna troll; but also, maybe we shouldn’t feed them / write off a project that seems like it is developing into something kind of interesting because of them.
My main gripe is that I wish it was open source. But at the end of the day, beggars can’t be choosers, and there are other open source examples for other synths that we could build upon:
i’ll reiterate that initially i was all for it and had a this is very cool attitude about it, but that’s because I could see that it was a plausible idea. Then i saw people giving the devs flack and didn’t understand why, but then I said there’s some strong criticism, then i was asked for proof that there was some strong criticism, then I supplied that proof. I have no horse in the game. I didn’t go for it because I didn’t want to create an account or whatever they wanted. I’m using like 6 different AI generators for words and pictures and none of those demanded i needed to sign up for them. Vital’s a different story, I signed up and even tithed. 
1 Like
Well… OpenAI require you to sign up to use their service. And they are (imo) a fairly reputable company. Or did you mean that signing up is merely an inconvenience versus it being some kind of proof of being a shady company?
Honestly trying to get clarification so I can understand you better.
@reklamchef I’m not sure if you misread/misinterpreted my previous post, but this part was directed at you/the proof you gave:
And then the rest of the post was me musing on why there seems to be so much FUD/dislike in general (not aimed at you), and providing relevant context/links/etc as I have observed them + my personal opinion based on that
This part I’m a little more confused about though:
Maybe it was different originally before I came across it, but for as long as I have known about the project, it’s never required any kind of sign up/sign in to download it. Both the download link, and the web version are open access:
I mentioned this thread on Discord, and the devs agreed that some of their initial releases were a bit hacky/messy; so perhaps that’s where the initial hate came from, and the ‘noisy troll’ side of people just haven’t bothered to update their opinions / seek further evidence since:
Maybe less relevant to this forum, but apparently a model that works with Serum is coming soon as well:
We may be living in parallel universes, but in mine, right now on the links you provided:
- download for the beta release requires a Discord sign in
- download for the legacy alpha release is a button that literally says “Sign in to Download”
- the button to launch the app literally says “Sign in to start generating presets”
1 Like
Ah yup; have just looked again and it seems their site takes a while to register the fact that I was logged in. So when I looked at the top right corner, it looked like I was logged out; which a few seconds later, changes to show i’m logged in; but by that stage I was already looking at the download link that had become available.
So yeah, my bad, memory fail. Signing up to get access was such a low friction and standard practice that it didn’t even register in my memory that I did so at some stage.
Not logged in:
Logged in:
But since it seems the only ‘protection’ signing in has is which part of the frontend source code it decides to render:
You can just extract the direct download link anyway:
That said, the legacy version is pretty outdated at this stage, and if you actually care to check out the program, I would recommend signing on to the discord and getting the beta downloads (which tbh is a pretty low effort thing these days, and pretty standard practice for MANY programs and communities… so I guess if that’s too much of a barrier for people… perhaps living without the tool and/or with their outdated beliefs is a better outcome)
I’ll just say I went to download it in the beginning and for some reason I didn’t feel like doing whatever it was the signup process wanted. And in the beginning of this thread I was super positiive. I don’t have any personal criticisms of the project myself, somebody put a question in my mind then I remembered I was a fan of the idea in this thread, so I felt some small bit of responsibility to call it into question, in case there was any chance it was some kind of red herring or whatever. No ill will or trolling intended on my part. I don’t see any reason why AI couldn’t be used to train Vital, but if they were pulling a fast one somehow, I wouldn’t want to promote, that’s all. The concept should work out, as long as there’s serious attention towards that effect. Godspeed Micromusic, Godspeed Vital Forumers!
2 Likes
nods valid.
Yeah, definitely. For anyone interested in stuff in this space; this definitely isn’t all of the research out there, but I started collating a list of AI patch generation projects / research / etc on this gist (and will add to it more over time):
1 Like