[a / b / c / d / e / f / g / gif / h / hr / k / m / o / p / r / s / t / u / v / vg / vm / vmg / vr / vrpg / vst / w / wg] [i / ic] [r9k / s4s / vip / qa] [cm / hm / lgbt / y] [3 / aco / adv / an / bant / biz / cgl / ck / co / diy / fa / fit / gd / hc / his / int / jp / lit / mlp / mu / n / news / out / po / pol / pw / qst / sci / soc / sp / tg / toy / trv / tv / vp / vt / wsg / wsr / x / xs] [Settings] [Search] [Mobile] [Home]
Board
Settings Mobile Home
/wsg/ - Worksafe GIF

Name
Options
Comment
Verification
4chan Pass users can bypass this verification. [Learn More] [Login]
File
  • Please read the Rules and FAQ before posting.
  • Supported file types are: GIF, WEBM

08/21/20New boards added: /vrpg/, /vmg/, /vst/ and /vm/
05/04/17New trial board added: /bant/ - International/Random
10/04/16New board for 4chan Pass users: /vip/ - Very Important Posts
[Hide] [Show All]


[Advertise on 4chan]


File: agent-47-funkytown.webm (4.4 MB, 1268x720)
4.4 MB
4.4 MB WEBM
Previous thread >>5493415
Due to high interest, there is now a dedicated suno thread >>5506204

Post anything AI generated. Song covers, animations, etc.
OC encouraged, but not required.
This thread focuses on audio and video with an audio component.
Let me know if you have more links to add. This thread is a work in progress.

> Voice-to-Voice
RVC walkthrough (somewhat outdated, collab is dead): https://docs.google.com/document/d/13_l1bd1Osgz7qlAZn-zhklCbHpVRk6bYOuAuB78qmsE/edit
Models, mega links, and mirrors: https://docs.google.com/spreadsheets/d/1tAUaQrEHYgRsm1Lvrnj14HFHDwJWl0Bd9x0QePewNco/edit#gid=0
https://github.com/Mangio621/Mangio-RVC-Fork
https://github.com/Vali-98/XTTS-RVC-UI
https://github.com/voicepaw/so-vits-svc-fork

> Text-To-Speech
https://github.com/collabora/WhisperSpeech
https://github.com/myshell-ai/OpenVoice
https://github.com/yl4579/StyleTTS2
https://github.com/BoltzmannEntropy/xtts2-ui
https://github.com/daswer123/xtts-webui (Warning: Windows version uses prebuilt binaries that anons haven't verified. Use at your own discretion)

> Music
> Online / Freemium
https://www.suno.ai/
https://www.udio.com/
https://www.stableaudio.com/
> Offline / FOSS
https://github.com/facebookresearch/audiocraft
https://rentry.org/AudioCraftRemix

> Vocal Cleanup
https://github.com/Anjok07/ultimatevocalremovergui
https://github.com/resemble-ai/resemble-enhance

> Related boards
>>>/g/sdg
>>>/g/lmg
>>>/g/aicg
>>>/h/hdg
>>>/e/edg
>>>/d/ddg
>>>/b/degen
>>>/vt/vtai
>>>/aco/asdg
>>>/aco/csdg
>>>/trash/sdg
>>
File: mint-bustin.webm (4.13 MB, 1066x720)
4.13 MB
4.13 MB WEBM
Extra reminder that there is now a dedicated thread for suno.ai due to the high amount of suno posts relative to other content.
>>
File: lotr-short-intro.webm (4.38 MB, 720x576)
4.38 MB
4.38 MB WEBM
>>
can anyone with an rtx 4090 use subtitle edit's ai subs (engine:purfview's faster-whisper) with a jav downloaded from https://sukebei.nyaa.si/ (must be at least more than 2 hours and 30 minutes like ABF-094) and tell me how long the eta was along with the actual time it took and with the code of the jav you used also with screenshot for confirmation
>>
>>5504578
What can possibly top this?
>>
>>5515280
This.
>>5506729
>>
>>5515281
it's fine but not even close to as funny
>>
File: the-story.webm (2.62 MB, 1280x720)
2.62 MB
2.62 MB WEBM
Anyone know where that riff at 0:10 comes from? I swear I've heard it somewhere before
>>
>>5515283
>I swear I've heard it somewhere before
Sandstorm by Darude.
>>
>>5515198
I'm on it. Wait for me here.
>>
>>5515457
hello?
>>
File: House Party Bash.webm (2.39 MB, 720x720)
2.39 MB
2.39 MB WEBM
>>5515011
I'm having a lot of fun with the software
>>
File: Canciron del Pirata.webm (2.4 MB, 552x552)
2.4 MB
2.4 MB WEBM
>>
File: 1704787632783944.webm (3.95 MB, 720x480)
3.95 MB
3.95 MB WEBM
>>
ym4dm
>>
File: BATMAN.webm (3.1 MB, 854x480)
3.1 MB
3.1 MB WEBM
>>
File: 1684424900620419.webm (5.41 MB, 320x180)
5.41 MB
5.41 MB WEBM
>>
>>
File: Megumin - leekspin.webm (2.83 MB, 320x320)
2.83 MB
2.83 MB WEBM
>>
>>
File: stukkie wukki.webm (636 KB, 586x302)
636 KB
636 KB WEBM
>>
File: 1685266785118026.webm (2.26 MB, 408x720)
2.26 MB
2.26 MB WEBM
>>
>>5516725
Oh , noooooooooooooooooooooooo
Poor people steal from the rich.
Noooooooooooooooooo
I am amrimutt capitalist lover. I always side with rich. Only they can steal and exploit the poor. The poor should never steal from the rich.
All my problems are because of the jews and because of the niggers.
>>
File: 1688609170664529.webm (666 KB, 512x768)
666 KB
666 KB WEBM
>>
File: geralt.webm (836 KB, 692x414)
836 KB
836 KB WEBM
>>
File: geralt2.webm (262 KB, 830x891)
262 KB
262 KB WEBM
>>
File: devil.webm (3.82 MB, 800x384)
3.82 MB
3.82 MB WEBM
>>
File: triss.webm (1.43 MB, 1280x640)
1.43 MB
1.43 MB WEBM
>>
File: oldfag brooks.webm (5.81 MB, 480x360)
5.81 MB
5.81 MB WEBM
Interest for AI voice funnies has really tanked huh?
>>
File: tpd-now.webm (1.1 MB, 480x480)
1.1 MB
1.1 MB WEBM
>>5515011
Wanted to polish this up for my YouTube channel, but decided it wasn't worth it. Here you go, guys.
>>
>>5519545
i can understand that since the pasta got stale in 2022
>>
>>5519552
Eh... I feel like it could've worked if I came up with some funnier things to do to postmodernists. I just kinda ran out of ideas lol
>>
File: rock-with-yuu.webm (4.59 MB, 1064x720)
4.59 MB
4.59 MB WEBM
Speaking of youtube, anyone else upload covers there? I just ran into a weird issue with the content detection system. I did a cover album and it seemed to allow quite a few songs at first, then when I went to make it public it changed its mind and decided all songs were blocked in all regions. I'm not sure what happened but it seems like it decided to block them all when I added descriptions.
Anyone else experience this weirdness? It's like impossible to know what will and won't be blocked now. One of them was this, and historically the Michael Jackson catalogue has been fine. You think they're specifically blocking AI covers now?
>>
File: 1707751697455051.webm (2.9 MB, 600x600)
2.9 MB
2.9 MB WEBM
>>
File: 1675825450603696.webm (637 KB, 1080x1920)
637 KB
637 KB WEBM
>>
File: 1677061457265442.webm (4.66 MB, 960x720)
4.66 MB
4.66 MB WEBM
>>
>>5519554
people keep making that pasta with ai, if i've heard it once i've heard it 100 times so it's an instant close after 1 second. i can't imagine any anon sitting there listening to the whole thing, eager to find out how that particular voice will pronounce the same words you've listened to so many times before.
>>
File: lynchian.webm (1.81 MB, 960x540)
1.81 MB
1.81 MB WEBM
>>
File: if you insist.webm (4.07 MB, 720x720)
4.07 MB
4.07 MB WEBM
>>
File: lamp.webm (1.93 MB, 800x480)
1.93 MB
1.93 MB WEBM
>>
>>5515283
what a time to be alive
>>
>>5519600
Well... I mean I didn't just do the usual list of deaths you hear in a "kill / behead / roundhouse kick" pasta. Sure I did the first three (you have to do the first three), but after that I tried to get creative.
Here's the full pasta I wrote for him:
> Kill postmodernists.
> Behead postmodernists.
> Roundhouse-kick a postmodernist into the concrete.
> Send a postmodernist into space without oxygen.
> Gaslight postmodernists into thinking they aren’t smart enough to understand the artistic reasons why you’re killing them with actual poison gas.
> Light a postmodernist on fire.
> Push postmodernists into industrial lathes.
> Strap a postmodernist’s balls to a surgical table under a hydraulic press, and say you’ll free him if he can define “crush” before the machine finishes a cycle.
> Use false rape accusations to ruin a postmodernist’s life.
> Grind up a postmodernist in escalator machinery.
> Trap postmodernists in an elevator before cutting the power and severing the cables.
> Hang postmodernists from every lamppost, up and down Madison avenue.
> Throw postmodernists out of helicopters.
> Suck postmodernists up into jet engines.
> Hurl postmodernists into active volcanoes.
> Cancel postmodernists on Twitter.
> Grind up a postmodernist’s baby in a woodchipper, point the discharge chute at a canvas, and tell the parents the result is a long-lost Pollock before demanding they defend its artistic merits.

> Total Postmodernist Death Now.
>>
>>5516742
Pretty good but annoying how you can tell when the AI and normal voices cut in and out
>>
>>5519579
Can you make an Odysee or Rumble channel for your blocked stuff Chameleon anon? It should be better, especially for music stuff.
>>
>>5520074
Yeah that's probably the way to go. I keep telling myself I'll make an Odyssee account and I think I'll work on that this weekend.
>>
>>5520074
>>5520123
i thought odysee was about to be shut down because they had financial problems? have they been sold or is hanging on by a thread?
>>
File: yuu-make-loving-fun.webm (5.94 MB, 720x414)
5.94 MB
5.94 MB WEBM
>>5520074
I feel like there was little point in putting this one on Odysee since it's a joke based on an already obscure vtuber, but here it is.
https://odysee.com/@ChameleonAi:1/yuu-cover-album:e
>>
File: kek.webm (5.99 MB, 1024x768)
5.99 MB
5.99 MB WEBM
>>5518697
>>
File: dunkin.webm (2.81 MB, 854x480)
2.81 MB
2.81 MB WEBM
>>
File: 1711365530999492.webm (1.67 MB, 686x384)
1.67 MB
1.67 MB WEBM
>>
File: sonic.exe.webm (1.23 MB, 870x870)
1.23 MB
1.23 MB WEBM
>>5521339
i wanted to post the one where sonic and shadow runs next to each other talking, but lost it. anyone have it? not sure if it was ai, i think not.
>>
File: soldic.webm (5.18 MB, 500x500)
5.18 MB
5.18 MB WEBM
>>
StyleTTS2 output file put through RVC. Only the RVC model was fine tuned. Karolina Zebrowska audio I gathered was denoised with Resemble Enhance and de-reverbed with Izotope RX 10.
>>
for the requester in the waifuy /co/ thread. it turned out pretty good imo.
https://vocaroo.com/1fzbtfJvVoIB

For the huntress wizard requestor (if you're around), it may take a little bit longer than tonight because I need to find her voice clips and train a model for her, but I haven't forgotten.
>>
>>5521731
damn I really butchered that first sentence
>>
>>5521678
Sounds like you trained a decent RVC model. The TTS sounds like TTS but that ain't bad considering it's all local.
Isn't Izotope paid software? Ultimate Vocal Remover has de-reverb and de-noise models, in case anyone is interested in the possibility of a fully FOSS solution. UVR is pretty versatile and not just for separating music.
>>
https://vocaroo.com/1hKUqFxegPOr
>>
is whisper ai good for javs?
>>
>>5521731
https://vocaroo.com/1eOMEWUsQFBf

Here's the Nya Nya Huntress Wizard.
the model turned out great lol, thank god she has a standup special so I could get so many clips
>>
https://vocaroo.com/1iONv5xfSD7A
>>
File: red dead redemption.webm (5.91 MB, 498x280)
5.91 MB
5.91 MB WEBM
>>
>>5515011
I wish I could still enjoy hearing funkytown.
>>
>>5523327
Hey Anon, why the long face?
>>
>>5515011
Ice Ice Matrix AI edit
https://www.youtube.com/watch?v=gnEIeVWLtbU&pp=ygUKYXVyYWxuYXV0cw%3D%3D
>>
who can convert this to a webm?

files.catbox.moe/zsgi5k.mp4
>>
I stumbled upon some anons talking about the spiked forest of nuclear waste sites, so I made an AI music video of it.
The lyrics are loosely based on this:
https://en.wikipedia.org/wiki/Long-term_nuclear_waste_warning_messages
Also, if anyone could give me pointers on how to make higher resolution webms with lower file size, that would be helpful.
>>
>>5522243
I haven't tested it on them, but whisper tends to have trouble with not clearly pronounced text.
JAVs have both massive noise and extremely irregular pronunciation.
>>
>>5523866
ffmpeg. If you have any questions, consult the man page.
>>
>>5523890
There's only so much you can do. Use vp9 and 2-pass encoding, reduce the frame rate, if audio is less important, reduce audio bitrate.
For that webm since it's a slide show you can get away with like 12fps.
>>
File: ghost.webm (4.79 MB, 640x480)
4.79 MB
4.79 MB WEBM
>>
>>5524504
Bit of a banger you've got there, mate.
>>
>>5524504
yeah dude, that's fucking good.
>>
>>5524504
holy shit, its actually good
>>
>>5524504
really makes me think of Within Temptation
>>
>>5524029
I'm just jealous of some of the webms in the anime threads. Some of them are just pure quality.
>vp9
Check VP9/Opus, right? That's already checked by default in Webms for lazys.
>2-pass encoding
Not sure where to find that in WfL.
>12fps
I wanted to set it to 15 instead of 30, but the program just stuttered at the start and refused to convert. Maybe I'll check the video editing program for lower frame rates next time.
>>
>>5518706
lol, nice
>>
>>
>>5521531
honestly one of the most banger AI covers
>>
>>5517608
Based, what was the prompt for this?
>>
>>5523890
meanwhile
>waltzes into the pyramids and takes the treasures
>>
>>5525062
dutch, sea shanty, trains - style
the lyrics are just whats on the sign
>>
>>5524601
If you can't specify 2-pass, use something else like Handbrake or ffmpeg command line.
>>
Did a couple of these as a joke cause a friend of mine plays Fallout 76. Turns out HL Scientist works well for older songs.
>>
>>5525200
>>
This was wonderful anon. Thank you for making this for me.
I loved it so much, I drew her singing it, just for you.
Something is preventing me from posting the picture so please take this catbox instead.
https://files.catbox.moe/vvqyny.png
>>
>>5523041
I can't listen to the original anymore. It has to be the WoW Parody of it.
>Grind baby, grind baby, but not the leveling kind.
>>
File: HLScienWorldOnFire.webm (2.63 MB, 320x240)
2.63 MB
2.63 MB WEBM
>>5525203
Did this one too but it's not as good as the other two. (Also he kinda has a stroke near the end for a bit.)
>>
>>5524029
i'll add a trick, blurring the video a bit could make it compress better (this is for very low bitrate visuals since otherwise you'll see the blur).
also lowering framerate too much doesn't work all that well for videos that doesn't change much, codecs usually understands that it is still images and won't repeat data. what you want to increase is the max time between keyframes since data is forced to repeat then.

>>5524601
anime/cartoon tends to compress well with the clean colors everywhere that stays the same between frames, don't expect to get that quality
>>
File: Southin Park.webm (3.99 MB, 480x480)
3.99 MB
3.99 MB WEBM
>>5524633
i think this south park cover is my favorite, the voices fits well and sounds right
>>
File: out of touch.webm (1.56 MB, 728x720)
1.56 MB
1.56 MB WEBM
>>5525200
>>5525203
you're right, suitable voice for those songs
>>
>>5525205
BLESS Anon! I love it!

And you probably can't post it because it's not animated
>>
>>5525320
If I knew how to animate, I would have her sing for you. Ah well. Catbox is just as good. I'm glad you like her. I enjoy drawing Marcy.
>>
>>5525329
If you have any ideas for Marceline, please let me know.
>>
>>5525329
you're a king anon. thanks for the art!

>>5525341
another anon making marceline covers, my collection grows doubly
>>
>>5525346
Hmm. I need to hear some more Marcelines. Post some random one and I'll take an idea.
>>
File: 1349789609146.gif (134 KB, 250x120)
134 KB
134 KB GIF
>>5525363
https://vocaroo.com/1h8iKnru5et3
https://vocaroo.com/1lKswf7BCtqw

are a couple of my favorites I've made of her. She's got a great voice for songs without too much vocal fry
>>
>>5525367
Mhmmm. I think I may have just the right idea.
>>
[1 / 3]
>>
File: Silly Music.webm (2.21 MB, 512x768)
2.21 MB
2.21 MB WEBM
>>5525693

[2 / 3]
>>
>>5525694

[3 / 3]
>>
File: preacher.webm (4.43 MB, 480x270)
4.43 MB
4.43 MB WEBM
>>
>>5525693
Can you read?
Dedicated Suno / Udio thread
>>5518247
>>
>>5525205
>Something is preventing me from posting the picture
You can't post pngs on /wsg/, either convert to .gif or post catbox links.
>>
>>5525964
better thread
>>
File: Tiny-Tim-Hl2-Zombie.webm (1.96 MB, 300x374)
1.96 MB
1.96 MB WEBM
fresh oc
>>
>>
>>5525212
Another one.
>>
File: txf-pepe.webm (4.81 MB, 720x480)
4.81 MB
4.81 MB WEBM
OC
>>
>>5526671
saved
>>
>>5526278
pls don't ruin this thread just because your music schlop becomes a drop in a bucket in the proper suno thread
>>
>>5527158
lol very good
>>
File: SFS.webm (5.69 MB, 720x480)
5.69 MB
5.69 MB WEBM
>>5515011
>>
File: six_million.webm (2.2 MB, 512x768)
2.2 MB
2.2 MB WEBM
An A.I. classic.
>>
is there a software somewhere that would allow me to remove a specific song from another audio track? (i don't mean vocal isolation, i mean actually removing one track from another track)

tried doing it manually with audacity but the result was pretty scuffed, but the only AI-supported applications i've found so far have been for vocal isolation
>>
>>5528072
Unclear what it is you want to split out, but have you looked at all the different Ultimate Vocal Remover models? There are MDX-NET models that split bass, drums, noise, and other stuff.
If you're looking at something like a movie where you'd have to split out sound effects from the backing track, I'm not sure if there's a good model for that, but in general UVR would be the right tool if someone trained a model for it.
>>
>>5528232
i tried a couple of tools, including UVR, to split the track but it didnt work how i hoped. it is movie footage, where there's a song playing (which has its own vocals) and also characters talking and also sound effects, and i'm trying to get just the characters talking + sound effects, or at least just the characters talking without the song's vocals. sadly most models seem to split the singer and the dialogue into the same track, which is why i'm hoping to find a tool that will remove an entire song that i give it because i have the song in question, separate from the movie, but the stuff i've tried on audacity hasnt worked out too well.
>>
>>5528249
Try UVR MDX-Net Main on the first pass, then Karaone 2 (or VR Karaoke) on the vocal track. That will try to separate overlapping vocals. Getting the sound effects out of the instrumental track is a different problem. I don't know of a model that can do this. I don't know how it would know what is "song" and what is "sound effect". I'm not aware of any tools that can take in a song as truth data and separate anything that's not that.
>>
File: DeepFaceLive.webm (5.81 MB, 720x404)
5.81 MB
5.81 MB WEBM
>>
>>5528249
>>5528523
I'd do VR Arch - UVR-BVE-4B_SN-44100-1, it's meant for separating two or more voices singing at the same time.
>>
>>5528709
I should clarify that I'd use MDX23C-InstVoc HQ first, then BVE on the isolated vocal track. Not sure about the sound effects, though. You could put the instrumental into Audacity and just cut out all of the music manually.
>>
>>5528523
>>5528709
sadly neither of these worked-- both sets of vocals ended up on the main track. i figured there might be some sort of tool which could read a specific noise (e.g. a song) and remove just that noise from an audio track, which would avoid the guesswork involved in pure AI tools, but it seems like nobody's made a tool like that. thank you for the suggestions anyways
>>
>>5528898
You would think that would be a thing, but someone smarter than me can probably explain why there's no tool that can separate out the difference between input audio vs the same audio comped into something else.
>>
>>5515011
why is there /g/aicg in here but not /vg/aids? Aren't they one of the first generative ai general, or are we gatekeeping?
>>
>>5524623
damn I feel like grandpa over here with rvc, i've been out of it for a few months and you guys have posted some pretty good shit, I love this one. >>5524504
>>
>>5529349
Of course not. I just inherited the list from another that didn't have it, I'll put it in.
>>
this thread will live
https://vocaroo.com/10lDvNbtFV86
>>
>>5528524
this needs to be stickied on the front page of twitch to constantly remind everybody
>>
File: ララ.webm (3.9 MB, 852x478)
3.9 MB
3.9 MB WEBM
>>5515198
>needing subs for JAV
ngmi
>>
Love the Witcher posts
>>
>>5515283
Holy fucking kino.
Entire jewish media on suicide watch.
>>
>>5519493
I spent several days and attempts trying to make an Emma Watson model. It never worked and then using them for text to speech was ridiculously slow making it impossible to use for books.
>>
>>5530531
How did you source the audio? I find that I get best results when the audio levels are fairly consistent across all clips. They can be from multiple sources as long as the quality and levels are fairly consistent across them all. Best case scenario would be if she read an audio book or did a podcast. Gathering a bunch of short clips from random places is not even worth trying, it'll sound like crap.
>>
>>5526671
based
>>
>>5526671
kek and saved
>>
File: announcement.webm (2.17 MB, 300x365)
2.17 MB
2.17 MB WEBM
posting a classic
>>
>>
>>5531626
god these are so cursed. 10/10
>>
This is not done yet but i probably won't finish it anyway
https://voca.ro/16KjKsMvnfjr
>>
File: Indoctrination.webm (5.74 MB, 484x482)
5.74 MB
5.74 MB WEBM
>>
>>5524504
This unironically slaps. Well done, anon.
>>
Infinite possibilities and anons can't stop dedicating content to trannies lmao
>>
>>5532891
we're shouting about the fire burning behind people and they just refuse to turn around, have to shout louder if we want to stop it from spreading
>>
>>
>>5532920
Stop shoving trannies down my throat.
>>
>>5532991
there's a fire burning behind you dude, put it out before your sister or your sister's daughter gets raped in the women's bathroom.
>>
>>5532920
You could have just said "I find it funny" but no, you had to be cringe.
This is the same kind of attitude of people who think that changing the color of their profile picture enacts social change.
>>
>>5533010
Give me the stats on this bathroom rape epidemic.
>>
>>5532920
>>5533010
How does it feel being psyoped by the Manhattan Institute?
>>
>>5533028
there's nothing funny about trannies.

>>5533072
i will waste time on you anon. wait for my response.

>>5533074
very intellectual, did you write this after cutting off your tits?
>>
wtf is happening in this thread
>>
>>5533725
terminal troon obsession
many such cases
>>
>>
>>5533903
Spooky.
>>
>>5534338
>Spooky.
How so? I'm not getting any uncanny-valley vibes from that.
>>
>>5534470
you should
>>
i will continue to fill this thread with only adventure time content
>>
>>5535085
You won't see me complaining.
>>
File: AI_knows.webm (2.25 MB, 318x480)
2.25 MB
2.25 MB WEBM
>>5534470
Creepy af that a "democratic" government is using AI creations to be their public officials
>but a dream for corporations and oligarchs, who no longer need to deal with humans for their control mechanism
>>
>>5535602
i mostly saw it as a "this 'person' cant be killed and has no family or relations here or anywhere so its a safe public figure". its sorta like a mascot to me. but I understand where you're coming from.
>>
>>5524538
>>5524566
>>5524585
>>5524600
>>5529570
>>5532884
Thank you, anons. I've uploaded the extended version on yt with a couple of more on the side: https://www.youtube.com/@soulseashell2553/videos
>>
File: fgfp.webm (2.07 MB, 1280x720)
2.07 MB
2.07 MB WEBM
close but no cigar on this one
there's so many fun AI tools I can't keep track these days
>>
>>5536280
this is ai? feels like people are merging things that used to have several names into just calling it ai. for example referring to a face filter as ai. what used to be an applied algorithm is ai.
>>
>>5536829
>what used to be an applied algorithm is ai.
first time?
>>
>>5536900
i'm just noticing consolidated terminology. what's beneath haven't changed.
>>
>>5536829
Viggle definitely applies machine learning in some capacity, pose detection and rotoscoping at the very least. It also looks like they've automated some other traditional visual effects techniques, and that's my guess on why it looks less like AI and more like mocap.
>>
>>
File: It's Ma'am_3.webm (3.99 MB, 512x768)
3.99 MB
3.99 MB WEBM
I just started with Suno but HOLY FUCK does it make it so easy lmao
>>
https://www.youtube.com/watch?v=L2gn8UA3NfM
>>
>>5536829
Anyone in IT will use "AI" all the time to sell fucking anything for the near future.
Same shit as with the "blockchain" before that.
Both have their reasonable applications, but what that guy is trying to sell you is (a) probably not reasonable and is (b) probably neither "AI" nor "blockchain" in a stricter sense.
>>
>>5538062
i've never seen blockchain used incorrectly but maybe you need to be an investor to get those tales
>>
>>5537790
Browsing that site I keep thinking "no way that's ai". But it really is this good now.
Seems to have a bit of a problem ending a song though, several just ends suddenly (you'd think it would just make it fade out at least).
>>
>>5538062
AI is definitely a buzzword for startups right now, but it's also a really low bar to be able to say something is AI. All it means is that you used machine learning in some capacity.
>>
>>5538167
>All it means is that you used machine learning in some capacity.
No, it doesn't "mean" even that these days.
You seriously have people trying to sell fucking sorting algorithms or Dijkstra as "AI".
That table your colleague did in Excel? That's "AI"!
>>
>>5538253
ok but the original comment was talking about viggle and by extension a lot of the silicon valley startups. Even the most grify corp has a legitimate if tenuous claim that they use AI because they use a neural network somewhere. We're not talking about some chinese or pajeet rando on insta who's farming imaginary internet points.
>>
>>5538166
Yeah Suno has a default 2 min limit. You can extend it but it doesnt work well and it extends it as another song, rather than continuing the existing one
>>
>>5515011
any way to add sfx to video using ai?
>>
>>5519493
lol that pewdiepie clip
>>
>>5515011
>AI upscaling for old videos
I've been looking for a solution to use AI upscaling for old videos. I've already tried some cv2 methods, but most of the results just give me an upscaled, blurred mess. I know there are some paid software or web apps that can do it, but I'm interested in free tools. Does anyone have experience with free tools for AI upscaling and achieving good results?
>>
the double
https://vocaroo.com/1niXvt0e0ymQ
https://vocaroo.com/1d8cGZkkBlkH
>>
File: weird ai.webm (5.94 MB, 480x272)
5.94 MB
5.94 MB WEBM
>>
File: 1713788587459060.webm (2.16 MB, 640x360)
2.16 MB
2.16 MB WEBM
>>
>>5537734
How lovely.
>>
>>5538819
>Anon Finn.
Adorable.
>>
>>5533903
You can really tell their leader is Jewish
>>
>>5538322
you just click on the ... of the page of the second part and it gives you the option to merge them after to make a whole song
>>
>>
>>5540522
whoa that was a saga
>>
>>5535602
>AI_knows
isn't it kinda batshit how grown adults create literal fiction and pretend that it's somehow proof of their narrative lmao
>>
>>5540522
Would have been better without the tiktok zoomer attention keeping video in the background. Did you edit this in or did you just rip the vid from some site?
>>
>>5540270
Thanks, i liked it too
>>5540272
had to break out my MS Paint skills for that one, so thanks

https://vocaroo.com/1cgEFVKfdy04
This one turned out pretty good IMO. listening to the lyrics 12 times to get the right tunes hit different since its one of my favorite songs.

unfortunately tho, she couldn't hit one of the last yells and there are some weird artifacts in the instrumental which might be vocals that I just couldn't get out. if anyone has any other ideas than MDX kim vocals and VR Karaoke to maybe clean up the instrumentals, I'm all ears.
>>
>>5538976
holy shit I love this so much.
>>
>>5523041
HW causes such a violent physiological reaction in my balls that i wish they actually swelled as if i were some type of animal to have this feeling reinforced. i NEED sex with HW i NEED to inhale her odor. even hearing her talk, let alone sing, makes me want to blow a load in my underwear prematurely just to further concretize my sexual attraction to her
>>
>>5541410
Settle down, Finn.

Her voice really would be a delight to hear sing. Imagine her singing wistfully to herself some old, celtic-esq love ballad with strong allusions to her and Finn. Oh. That would make my heart smile.
>>
>>5541410
i understand friend, but maybe take a cold shower lol

>>5541571
i couldnt get anything Celtic or Irish because most of the love songs are really breathy and the AI just gets too crusty when trying, but I've got these two which I like

https://vocaroo.com/1iSm4jRnL56a
https://vocaroo.com/1iouk9sjM3wd
>>
>>5541959
Ah.
Another fine addition to my collection.
>grevious.gif
>>
>>5541410
>>5541985
got any requests? im kinda running out of ideas for these two besides random songs I find on pandora or something
>>
>>5540522
I know that's made up but more than half of the girls in the world look average yet I don't think even 10% think they are average.

>>5540923
Why would anon put together something like that, come on. Obviously it was just "ripped" like you call it.
Must be truly awful growing up today. I hear some kids start feeling panicked from watching videos longer than 2 minutes.
>>
>>5517649
The average black has an economic impact of -700k dollars, adjusted after ALL his life's earnings.
meaning even weighted against the money he puts in the system, he takes the better part of a million dollars out of it.
The average legal hispanic takes "only" half as much out of the system.

The average white is at +200k. Positive. Literally everyone else is surviving off of the massive surplus created by the whites.


The average nonwhite is being paid to survive while they consume more than they create.
>>
>>5542299
Mmmm, I do but shes not from Adventure Time. is that acceptable?
>>
>>5542725
Sure. If the op doesn't have a model another anon made though it's gonna take me a while longer to train a voice
>>
File: ss.webm (3.49 MB, 854x480)
3.49 MB
3.49 MB WEBM
>>
Someone repost cute and funny song from a few threads back
>>
>>5542978
Well, alrighty then. Eclipsa Butterfly, from Star vs. the Forces of Evil. Something sweet, maybe with this. https://www.youtube.com/watch?v=vbEwUTjKwLU
She's a Metalhead, so if you have any heavy rock or metal song you like, she would probably sing that too.
>>
>>5525209
God hard like heroic and a good few others are so deeply ingrained my brain supplants the real lyrics with the ones from parodies.
>>
>>5543208
>Ain't got no epics.
>Ain't got no 'chievements 'cause I aint first rate.
>Can't even claim Naxxramas-
>-Butchu' know I'ma be your favorite group mate.
>Invite me, girl.
>>
>>5543214
damn i havent listened to Ulduar in over a decade
>>
>>5543171
i'll need to get the voice made so it'll take maybe a day or so since I'm a wagie
>>
>>5543171
alright, ive clipped a bunch of her lines as Eclipsa and an interview she did where she sounded pretty similar. I'll probably run the training overnight so I'm not tanking my pcs performance. Here's hoping I got good enough adio
>>
>>5543672
Good luck anon and make sure you normalize all the inputs first. I don't know what kinda hardware you have but it usually takes me about 24 hours on a 6750XT before something is fully baked.
>>
>>5543288
>>5543672
I eagerly await your creation.
>>5543285
Sometimes when I'm at work, something will remind me of WoW - which leads to that.
>>
>>5543171
I think it turned out pretty good. Hope you like it
https://vocaroo.com/1fFtv7KCenmV
>>
File: Don Roblox.webm (1.61 MB, 320x400)
1.61 MB
1.61 MB WEBM
>>
File: gandalf-watching-me.webm (5.89 MB, 640x268)
5.89 MB
5.89 MB WEBM
>>
>>5540522
lmao
>>
>>5544810
this is my favourite thing you've made yet.
>>
>>5544843
Thanks. I got a little bored doing straight conversions and am trying to do more with custom lyrics.
>>
>>5544871
yeah, I think I've gotten bored, too. not sure what to do. I'm not funny enough, or smart enough, to make original content, lol.
>>
>>5544810
fokken saved, sounds a little autotuned but very good
>>
>>
>>5544303
Not too bad, I liked it. Good job mate.
>>
https://youtu.be/Tav8EISUhYk
https://youtu.be/dgTHyvKlUJ8
>>
>>5544810
phenomenal, reminds me of 2007
>>
Could you guys make anything out of this?

Good boy.
Sit, roll and fetch.
Here are your orders.
Follow the rules.
Know your place.
Oh normie.
Pitiful slave.
To the hierarchy.
Instincts ingrained.
Parasites in charge.
Your leaders.
The chosen, the Z.O.G.
Your people the corpse.
The state your church.
Your nation a graveyard.
An infestation.
What a possession.
Of maggots and worms.
A reanimation.
Unholy, corrupted.
To be struck down.
By the divine.
>>
>>5545473
I have more.

A divine spark.
Born within a mortal body.
A vessel of time.
The sands of time slip by.
Each moment a grain of sand.
Every grain fleeting and flowing.
To never be repeated.
Moments cherished.
Appreciated when lost.
Until the very end.
The hour glass empty.
What amounts of life?
A mound of sand.
Representing death.
Your will, desire and belief.
Representing life.
Till the last grain.
A vast desert.
Past and present.
Howling winds.
Tinged by your mound.
Your voice echoes.
Your will immortal.
Your desire unending.
Your beliefs eternal.
>>
>>5545473
Try the suno thread.
>>5539607
>>
>>5545487
Will do, thank you.
>>
File: xbeezy.webm (436 KB, 1024x1024)
436 KB
436 KB WEBM
>>
>>5544935
I'm curious what parts you thought had that autotuned sound. Some of it was me and some of it was the real song so I wonder which sounded more artificial.
>>5545335
Thanks. I got the same sort of feeling while making it even though it was made using current year tech, the 20th anniversary blu-ray release, and the newer hobbit movies. It's kind of a strange feeling to make something new that sort of belongs to a time long past.
>>
>>5545837
>what parts you thought had that autotuned sound
i dont feel like going through the whole thing and reviewing, because it's hard to pinpoint sound and describe to someone else exactly where i mean.
the first place that i think sounded strange was 0:53 ("the watching me", in the middle of wa-tching, like the A getting higher).

biggest flaw in the track is 3:22 ("tell me, who can it be?", sounds like "tell me höw it be", where höw can sound like 'who' or 'let' or 'how')
>>
>>5545891
I'm always interested in someone else's analysis because I want to make them better in the future if I can correct for it.
Both of those are conversions from the original vocals. At 0:53 it's actually a harmony with Michael Jackson and Rockwell. Voice conversion is unpredictable with harmonies so sometimes the pitch will jump incorrectly. Harmonies are the bane of my existence and vocal remover can't always separate them cleanly. Oddly enough, autotune would have fixed that but I haven't found a FOSS autotune solution for linux and I'm working 100% FOSS.
The 3:22 is also a common problem with voice conversion, the hubert process sometimes mis-identifies the phoneme so it picked something in between who and how. This can sometimes be exasperated if the trained model is a different language or accent from the track being converted.
Interesting that the parts you identified aren't the same ones that kind of stick out for me after listening to the final product. Probably because I don't have fresh ears. For me, the part that I probably should have fixed is 2:36 where "who" got pitch shifted down ridiculously low to the point where it might not even register as words being spoken. That was my fault when recording and it probably would have been better with another take. Also some of my extemporaneous speaking at the beginning and middle didn't register correctly, but that's kind of a quirk of my real voice and I can only do so much about it.
>>
>>5524504
there goes the music industry
>>
>>5524504
damn, thats pretty good.
>>
i'm going through a couple of star wars fan films and converting the vader voices to james earl jonses. so far i'm doing shards of the past and pull to the light but are there any more that might be worth the trouble? i know others exist but the one's i've found are pretty low production quality like the costumes are terrible or they take place in an obviously real world setting, etc. Some other obvious things someone might be interested in doing, is a mod for the force unleashed and fallen order games. I imagine a lot of people would be interested in such a mod.
>>
>>5544810
Gold in a sea of shit.
>>
>>5547257
I have to see some of this. Post a couple clips?
>>
File: callmemarcy.webm (3.44 MB, 849x710)
3.44 MB
3.44 MB WEBM
not the original Marceline poster but i wanted to give it a try.

it came out decent but there are some weird artifacts still. i had to train my own marceline model. maybe more and better quality input audio would help get better output. at the same time i'm doing vocal isolation locally and that is definitely a limiting factor
>>
File: subs.webm (1.09 MB, 1272x692)
1.09 MB
1.09 MB WEBM
can anyone understand what the missing ??? word is in the second line of lyrics .. something that starts with a "b"?
>>
>>5547954
bangers maybe?
>>
>>5548006
doesnt really make sense as a conservative meme but okay thanks
>>
>>5526671
holy kek. this is inspired
>>
>>5547684
hell yeah anon, you mind posting a vocaroo link or something so I can get this as an MP3 more easily for my collection/mixtape?

https://vocaroo.com/1bCOTdTPQFz8
>>
Can someone plz post the LoTR Shire one with the simple white folks and no one else?
>>
>>5547954
really banger song dude, what are you planning to do with it?

maybe ??? is "faith"? like "bootstrapping faith and you know I got them all". it's AI so it could just be garbled nonsense but bootstrappin' faith would make some sense.
unless it's a name of some political leader in Israel or maybe a US politician who is really pro-Israel, since the lyrics sings about his boy not having love for Israel or that damn wall.

btw slowing down the webm it sounds more like he sings "conservative" in the first sentence but maybe you want to keep it as cuckservative regardless
>>
File: Shire.webm (3.99 MB, 992x416)
3.99 MB
3.99 MB WEBM
>>5548512
>>
File: jej preview.webm (4.23 MB, 852x480)
4.23 MB
4.23 MB WEBM
>>5547379
It's not perfect but close enough for me to find it entertaining.
>>
>>5548613
Can't expect it to be perfect unless someone is really good at a vader impression. I think this is a perfect application of AI voice.
>>
File: girlfromipanema_marcy.webm (4.74 MB, 850x1146)
4.74 MB
4.74 MB WEBM
>>5548121
https://voca.ro/18MNPeDmpDds

i have a couple more cooking too. if you have any suggestions for how to avoid the kind of artifacts like what happens here at ~0:47 and ~2:09 i'd love to fix it
https://voca.ro/18ERaYxXMAci
>>
>>5530560
Source audio was from some files someone else had compiled.
They are labeled:
Beauty and the Beast - Emma Watson Interview 1-4
HITRECORD, Technology is a Superpower
Time's Up Now
about anti-bullying and harrassment
interview for Colonia
EW 1 - 1
The Circle

Over 40 minutes of studio quality audio of only her voice. I tried using all of it and a smaller subset. Results always sounded generic american.
>>
>>5538648
I've used Topaz for a few movies. Would only recommend it for low quality shit like old vhs. You also need like 500GB space to keep a movie as .pngs if you want to remove retarded shit like encoded black borders without having that step drop quality.

REM set crop size
REM "/crop=x:y:w:h" starting position XxY, crop WxH
REM Drag image folder onto 'this file.bat'
REM output in original folder\cropped, DELETES ORIGINAL if cropped file was created for it
for %%f in (%1\*.png) do (
c:\_Programs\IrfanView\i_view32.exe %%f /crop=^(74,16,1888,1120^) /convert=%%~dpf\cropped\%%~nxf
if exist %%~dpf\cropped\%%~nxf DEL %%~dpf\%%~nxf)
pause
>>
>>5544810
Better than the movies. This took a shitload of human work.
>>
File: hope-marcy.webm (5.52 MB, 850x846)
5.52 MB
5.52 MB WEBM
>>5548766
https://voca.ro/1d6LKfqLPEz4
>>
>>5548766
big thanks anon.

i think you might have some luck with increasing the pitch filter and replacing the audio in audacity if that works, but idk. i didn't have that issue with this one.
https://vocaroo.com/1arb2GniKiUk
Though you may have also not used the frank sinatra version in which case there's no wonder I didn't have the same issues.

>>5548836
Also, thanks anon, love it
>>
Has anyone saved the "YOASOBIN" videos from Youtube before they were removed?
>>
File: 2024-05-14_18-37-38.webm (3.91 MB, 1920x1076)
3.91 MB
3.91 MB WEBM
>>5548766
I've done this song before.
Both of those sound like the instruments didn't get properly separated from the vocal track (the horns are bleeding through).
Try different models and multiple passes on the vocal track. For instance on this I did UVR MDX-Net Main and then ran the vocal track though a de-reverb model, either MDX-Net Reverb HQ or VR DeEcho-DeReverb I can't remember which. After that I did a 3rd pass with MDX-Net Karaoke 2 to separate the overlapping vocals in the second half of the song.
>>
>>5549232
>>5548844
thanks i appreciate the help! i'll try that out. i think you're right about the horn bleed-through. i was only separating vocals+instruments with Spleeter which only gets you so far
>>
>>5549232
i do UVR MDX Next Kim Vocals 2 into VR 6_HP-Karaoke on the lead vocals so i figured thatd be enough. i'll try that method out. thanks!
>>
>>5515283
this goes so fucking hard it's unreal
>>
File: lion king.webm (722 KB, 886x764)
722 KB
722 KB WEBM
>>
https://vocaroo.com/1kji5mTm7KC5
did the triple refine from above rather than my normal two process. i cant really tell any difference but that's probably because this song didn't have any horn-adjacent instruments
>>
>>5548565
thanks brokin
>>
>>5549550
that's bro + kin
not broken
I'm autistic btw
>>
>>5548648
yeah, I think the potential is there to be really close but like you said it's only going to be as good as the original impression.the most important thing seems to be having the right accent, cadence and such. in another thread someone said something like future voice actors are going to try to perfectly mimic the old ones for this reason and that's probably true.
>>
does anyone have the edit where hal sings vocaloid songs ?please post it
>>
>>5549735
>>
>>5549487
Yeah you only have to do multiple passes on a case by case basis.
>>5549639
We're on the cusp of ghost voices being a thing just like ghost writers. Anonymous people good at impressions or good at singing that provide the voice for famous people, and nobody's going to even know it.
>>
>>5549260
i did manage to get a better result with your suggestion. this process definitely helped, and honestly i think my problem was using Spleeter.

>>5549487
>>5549757
>case by case basis
in my limited testing with the different models and alternating different combinations of MDX main or karaoke, maybe this is obvious, but main splits all vocals while karaoke treats backup vocals and a second singer as an "instrument" for the purposes of vocal isolation (i.e. removing them from a vocal isolation and including backup vocals in the instrumental split). this has the secondary effect of better splitting instruments that overlap with vocal ranges (like the horn). at least that's my current understanding.
>>
>>5549753
thank you : )
>>
>>5548836
https://voca.ro/1nmlfenV3LBw
>>
>>5549980
>this has the secondary effect of better splitting instruments that overlap with vocal ranges (like the horn)
Yep that's right. In the same vein, a reverb model can have the same sort of secondary effect, so it's always good to test out different models if something didn't work the first try.
The most common second passes I do are karaoke and de-reverb.
When training voices, denoise is useful to remove microphone hum.
>>
>>5550094
bless anon, i've been doing nothing but misses with some of the songs I've been trying today so at least I get one today
>>
>>5548836
Mhmmm. this was nice.
>>
File: marcy_bangs.webm (4.01 MB, 551x551)
4.01 MB
4.01 MB WEBM
>>5550094
https://voca.ro/1hBi6hLrmRdj
>>
>>5551155
This sounds like this would've been a song she would actually sings about.
>>
>>5538819
This is really nice :')
>>
made this one about a month ago, but it's still one of my favorites. I go back to it all the time and am really happy when it randomly gets shuffled to.
https://vocaroo.com/1bBY1fGcWbDs
>>
i've now got 59 Marcy songs in my collection lol. thanks for the help anon.
https://vocaroo.com/1hBi6hLrmRdj
>>
>>5530513
>童貞度
I'm not clear on the meaning of 度 there...
>>
File: (YOU).webm (2.97 MB, 1920x1080)
2.97 MB
2.97 MB WEBM
>>>
>>
>>5549351
nice, though i've never heard the english dub of that movie
>>
>>5549757
>We're on the cusp of ghost voices
I'm just waiting for the white fix of the live action little mermaid.
>>
>>5552255
catchy!
>>
>>
>>5552691
/!\ alert /!\
the suno-esque containment thread has 404d so AI schlop is leaking into the handcrafted/parody AI audio thread
>>
File: compressed2.webm (3.69 MB, 450x450)
3.69 MB
3.69 MB WEBM
>>5515011
>>
>>5551704
>>5551503
Whoever the marceline anon is, any chance of a How Soon Is Now by The Smiths cover? I think that'd be legit.
>>
File: output.webm (3.95 MB, 485x480)
3.95 MB
3.95 MB WEBM
Boeing Whistleblower Ballad
>>
File: output.webm (4.97 MB, 485x480)
4.97 MB
4.97 MB WEBM
>>5553002
Sorry I'm retarded. Here's a version with audio.
>>
>>5552965
I gotchu on Sunday evening unless the other anon does it lul
>>
>>5538648
pirate topaz and play with the test lengths and models
>>
>>5551818
"degree of"
>>
>>5552691
>explicit chess
>>
>>5552965
https://voca.ro/1hcLgr8So1Fe

>>5553019
scooped, but more options are always a good thing if you want to post your results
>>
>>5553417
Score, thanks it came out pretty good. I don't want to come off as one of those youtube commenter 12 year olds asking for tons of shit but I have one other request and then I won't hound for any more. How about the Y2K song that you couldn't escape if you were alive at the time "I'm like a bird" by Nelly Furtado?
>>
>>5553417
Nice one anon! Not a critique or anything, but I might recommend lowering the instrumental volume a little since her voice usually comes out slightly quieter than the original so it gets drowned a bit.

>>5553543
Brother, i need requests lol. I've essentially run out of ideas until I hear something on pandora/spotify or from a YouTube playlist. Also I love making these so keep em coming
>>
>>5553543
>>5553568
that being said, im good for other voices too. i also find the process of making a training set and generating the model enjoyable. I just usually do Marcy because I'm hopelessly in love with a cartoon character and her voice ¯\_(ツ)_/¯
>>
>>5553568
>vocals drowned a bit
yea i had actually boosted the vocals a bit as well as mixed a second vocal track with an octave lower to help the vocals cut through. part of the difficulty is with how the original song's instruments support vocals for someone in a separate frequency range. that extra octave marcy needs to sound like marcy is sorta conflicting with the instrumentals. +12 or 0 semitone shifting is difficult for this song too, since both are outside marcy's normal range to begin with and there are a lot of high highs and low lows. i also considered a +5 or +7 pitch shift to better match her natural range at the cost of matching the original key with better believably/clarity. that was at least my process for this one
>tl;dr
shits hard i gotta gitgud

>>5553543
>i need requests... i've run out of ideas
basically this.
>"I'm like a bird"
cooking and i can throw other ideas at "how soon is now" if you want
>>
>>5553663
Finding vocals that are compatible with a voice is one of those unspoken things about AI covers that I wish was discussed more. Sometimes it's just a bad fit or a stretch.
>yea i had actually boosted the vocals a bit
Are you running a normalization pass on the vocals? That should take the guesswork out of how much you have to boost it.
>i also considered a +5 or +7 pitch shift
Oh hell no. If you don't do a full octave it'll just be off key. I've even tried doing this to get a good sounding vocal and then formant shifting to get into the right octave. None of it works.
>>
>>5553683
sorry, to be clear i meant pitch shift the entire song into her vocal range including the instrumentals as well as her voice clone.

>>5553663
initially im struggling to separate the layered voices with im like a bird. even without considering the harmonized vocals her main vocal track is cut and layered so ends of words overlap starts of the next word and ai really does not like that
>>
>>5553690
>including the instrumentals
Doesn't that just sound weird because the song is now on some odd key?
>>
File: example.webm (4.74 MB, 886x512)
4.74 MB
4.74 MB WEBM
>>5553698
yes but i only mentioned it to support my decisions for the end result i arrived at lol. in any case anything more than what i did initially is outside my current skill set and would likely require a DAW.

>normalization pass on the vocals
good suggestion and honestly idk why i didnt consider that sooner. thats on me
>>
>>5553683
>If you don't do a full octave it'll just be off key.
I disagree with this. it may be true sometimes, but usually a full octave is way too much. to keep things more natural sounding, I usually do a bunch of different runs at a 0.5 increase/decrease (depending) to have a transition more natural.

>>5553690
i found the same issue with a lot of indie pop. their vocals are so fried that the AI just breaks down every time lol

>>5553720
as a dummy, how would I run a normalization pass on some vocals that i have? is it an audacity function i can install?
>>
>>5553725
>is it an audacity function i can install?
Built into audacity. Select the vocal track and do Effect -> Normalize to 0 or -1 db.
>>
>>5553747
Nice, thanks. I assume I would do that before I RVC the track so it's a a little easier for the ai?
>>
>>5553782
No you do it after the fact since converting can make the vocal track quieter. 99% chance that the vocal track is already normalized going in.
>>
New Thread >>5553687
>>
>>5553873
New suno thread maybe but this one's not dead yet.
>>
File: 1677437053181696.webm (645 KB, 500x500)
645 KB
645 KB WEBM
>>5554017
he is borderline retarded, forgive him.
>>
>>5553873
The thread is nowhere near bump nor file limit what are you doing m8
>>
File: 1677427791721919.webm (400 KB, 500x500)
400 KB
400 KB WEBM
>>5554035
he's a functional dumb, give him some slack, jack.
>>
File: 1677426348196795.webm (489 KB, 500x500)
489 KB
489 KB WEBM
gotta complete what i got, wondering if any other fallout ai is out there. like lucy with her thumb up her ass as the ghoul eats her rancid cousin fucker pussy out.
>>
>>5553382
oh its a suffix? thanks
>>
Man, I hate to leave without offering another picture, I just haven't had the energy to draw lately. I'm hoping next thread I will.
>>
>>5553543
made it before the thread died
https://vocaroo.com/18ovm7n03Po0
>>
>>5554972
This was lovely Marceline-Anon. Thank you.
>>
>>5554997
no prob. Thanks for the requests, its been fun :)
>>
>>5555034
I only really requested Eclipsa and Wonderful, the rest were the friendly faces here.
>>
>>5555101
ah you're the artist anon. thanks again! I love the picture. I meant to make the webm with it, but didn't want to while the thread was still below the bump limit
>>
and a last one from me. The double to finish. thanks for the fun
>>
>>5555150
I had saved just the audio, but now? I'll add this, too. I just need to decide on what you have made to draw, just as above in the thread.
>>5555152
Nice, calming, sweet. A good song to end the thread on.
>>
>>5515011
is there anything decent I can setup on LM studio. I hate all the other setup options, docker always shits the bed



[Advertise on 4chan]

Delete Post: [File Only] Style:
[Disable Mobile View / Use Desktop Site]

[Enable Mobile View / Use Mobile Site]

All trademarks and copyrights on this page are owned by their respective parties. Images uploaded are the responsibility of the Poster. Comments are owned by the Poster.