#🧬│ai-chat
1 messages · Page 351 of 1
It's 0.1 my bad, pls use 0.5 - 0.6
So high amp threshold values can introduce noise
okay. but i did not like the output ? not sounds great. is there any other model ?
U want the vocals right? Or instrumental?
Try the MelBand Roformer Vocals by Kimberley Jensen
for Voc?
for inst ??
guys how do i download okada?
which gpu do you have ?/
I think, Mel Band Roformer Kim Inst V1 E by unwa
-rt
Interaction has expired, use the command again for a new interaction.
First link
rtx 4070 ti super
enough.. follow the linkks
ok
which Value Exactly??
Use 0.6
I think 1 is too loud
i want normal loudness
which audio actually have
well why you said this ?? if i can also change it form GUI
That was cause i dont remember the default value
Ye ik try with 0.6
i was again confused 🤣
for normalization or amplification
Amplification
and what about normalization ??
nothing happned 😭
chat i tried to upload a model and it says this
extension of file should be the following. pth,onnx,safetensors
Which model
🥺 it frustating idk what to do now
help me
Try increasing the normalization then. i'm not at home so i can't test
And what if u use 1 and 1
For both
should i create a public link for you ? if yes how ?
But I don't have audios. U should try with 1 and 1.
For sharing u need to edit run-UVR5UI.bat and add --share before the --open like this:
Xxxxx app.py --open --share
okay. can you ping me when you figured it out ??
Ok in like 3-4 hours
okay.. i will be sleeping on that time. but please inform me how to fix it..
Okke
Could I get recommendation for AI humanizers (local or online)
what ??
more precisely, I download the sound model from the server, throw it into voice.ai and it doesn't want to load
guys can anyone help me
when i try to upload a file into okada it says model file must be".pth"
Check #✦│chat message
why didn't you win?
why did you delete that
Noooooooo
Is there like a free website I can use on my phone to do text to voice?
google translator
wdym live
do u mean the live concert record and u want to remove the crowd?

Hi
understandable
bruh
ik
I am gigwon
im his alt
and it was spamming
like lagged
and it kept spamming i am gigwon
i wrote it 1 time
ane it started to spam
nah
wanna get banned for the second time?
mhm
did they nuke the majority of the ai cover videos off youtube?
why tho
hmm, maybe
are tutorials still online tho?
wdym
which tutorials?
okada tutorials
no idea, i've never even watched or seen any wokada tutorials on yt lmao
i hope they get deleted
they/them
AI Hub by Weights chan 
😭
i am gigwon
no one cares
I recently ran through the kaggles mainline and got to training the model, I was wondering how long it should take and what is considered too long meaning there must be an issue
how long its taking
its been about 45 minutes
and how many epochs?
1k
1000 epochs?!
how long is the dataset?
impossible to make 1000 epochs in 45 minutes
how many epochs should i do for 1h of time
how do i see
in #🏙│ai-images i showed what i see
if you dont know its fine, I will just redo it tommorrow
where would i find the console
also this is my first time, sorry i dont know much
are you using kaggle?
yes
on the kaggle page
dont refresh
also i dont reccomend kaggle or colab since they disconnect and/or ban pretty easily
kaggle is actually pretty good if you use ngrok for web uis and ive been afk for like 3 hours on kaggle and not gotten disconnected
i know people got banned tho
well i havent and its been almost a year since ive started using it
could be me getting lucky idk
cases by cases
best option is local, always
since paperspace banned rvc
best free option
for paid you could go on runpod and get h100s
how much?
pricy
codename has tried making pretrains with i think 8 h100s
and for a normal model?
no one that im aware of has tried making a normal model with a h100
what a waste
yo guys, im bored and wanna know what i should make ai playboi carti say
only worth for finetuning some flux model
Ку
hi
Hi. 
Make him say "wheh". 
yes
any good free ai voice generators that can do emotions or sound natural for conversations?
voice changer?
nah
damn 143 gb vram o -o
but like text to speech or anything that no talk needed
elevenlabs
is that noob friendly?😭
its easy :)
hold up... can i use custom voice model there
no
ohh you want with rvc models?
Custom model of what?
yes
you can use something i made
voice
RVC or SVC?
Last update: Oct 25, 2024

wait hold up
my grammar so bad so im gonna use translator first lol
u said ElevenLabs is good for natural speech n emotions, right? can i use the generated voice from ElevenLabs with other AI tools to add custom models?
sorry im new on this kinda thing
@stark scarab do you find out UVR Ui normalization and amplification glitch ??
you can download the audio from elevenlabs and import it ilaria rvc
oh ok
is there an optimal input-output ratio?
What do when me use VoiceChanger my ms 20000
change settings
what gpu do you have?
what gpu tho??
youre cooked
you cant use it properly
ai website about?
u could put a motion video over a photo
why
make the mona lisa break her jaw
gpu is too slow
it was face stuff only but the website had more things but thats all i kno
why? my friend have same GPU he ok
theres literally a watermark in those videos with the site youre looking for, you could take 2 minutes to actually be thankful to the only person that is trying to help you
lets move to #🔍│help-w-okada
oh so u 100% know
whats the site
look at the watermark
hey is there any tutorial in how to make these ai models with pytorch and tensorflow or whatever
I DONT REMEMBER IT
seems like a nice way to enter into learning ai
wdym
i wanna train my own voice model
-docs
- How to use RVC Mainline Colab by Cauthess
- AICoverGen Colab Guide by Eddy (Spanish Helper)
- Create a model with RVC disconnected (colab) by Angetyde
awesome thanks
no prob
wrong
its not the websute
site
not even close
its video thats as close as it gets
does anyone know how to make ai remasters
wdym by remasters?
like how do people make low quality shit into hq/cdq
they do it manually
wym manually
hold on heres an example
this is a hq (basically cdq) remaster of a song that originally leaked in like horrendously low quality
they probably manually did it, idk how to explain but afaik theres no ai that restore music
you mean to enhance low bitrate mp3? there is apollo as open source solution
yea i got apollo
🎬✨ Elevate Your Videos & Graphics with a Professional Touch!
Hi there! 👋
Need top-notch video editing or graphic design? I’ll transform your ideas into stunning visuals!
📽️ Video Editing:
Short/Long Videos, Reels, TikToks
YouTube Content, Event Highlights
Animated Intros
🎨 Graphic Design:
Logo & Branding
Social Media Posts
Flyers, Brochures, Infographics
Business Cards
📩 DM to view my portfolio & get started on your next project!
i offer one dolla
ho una foto mia la quale testa voglio fondere sul corpo di un personaggio di un fumetto quindi applicare la mia testa sul personaggio del fumetto assimilando anche lo stile del fumetto
non ne ho idea
This is an amazing song that has been made totally using AI. (not by me) https://www.youtube.com/watch?v=GH9b3lKIG9Y
BOnjour
Quelqu'un parle Français ici svp ?
j'aurais besoin d'aide svp
I need help please
how can i help you
I found a tutorial on YouTube that allowed me to unlock facefusion locally and that allowed me to use it as much as I wanted, but now it doesn't work anymore. Do you have a link to a tutorial to install a new version please?
sorry i dont know :(
what is the issue?
ERROR : python: can't open file 'C:\Users\my computor\Downloads\facefusion-unlocked-master\run.PY': [Errno 2] No such file or directory
hello guys what's the best ai dubbing ai possibly free on the market? or how can i make my own ai dubbing withmy pc? thank you
uh strange
wdym by ai dubbing? like what elevenlabs does?
Do you have a solution or a video tutorial to unblock facefusion locally please?
yes and heygen also
no im sorry, you should wait for someone else, good luck tho
so you want something local.. mh.. whats your gpu?
Tutorial videos on YouTube are outdated.
tinx Itaria
RTX 3060
There was one that worked but unfortunately it no longer existed.
i dont think its powerful enough for sometjing like this, also i dont think good open source options exist
Can chatgpt generate configs for cs2?
understand, thank you
configs?
no problem!
Its like game settings but you can make pretty advanced things, almost like a scripting language
do you have any suggestion on which platform is the best? can't see on their website how much 1 hour russian to italian video would cost me
i think it should be able then
Even if it doesnt know i can teach it the logic right?
my favourite is elevenlabs but there was another i dont remember the name
theorically speaking yes
What happens if you use chatgpt for somthing illegal?
nothing it will just stop working or respond with something like “sorry i cant help with that”
NVIDIA GeForce RTX 3060, 12GB VRAM, you can train a little bit anything there as it has 12GB.
Right but if you trick it
no one will come after you
?
maybe you get your account banned
Yeah alright i can live with that
Question is how well it understands cyber security and bypassing
From what i understand its not that great at generating code
If you type something illegal or inappropriate to ChatGPT, it simply just respond with "I'm sorry, I can't assist with that." But keep doing so can break the entire conversation with it.
Yeah its not that hard to bypass
You just have to frame what you are doing as something innocent
Does it save information between chats? Or can i just reload the page to start over?
Freaky. 
What is?
Uh. Send your link to #1159290752195633273.
Is this real? 
Guys, does anyone know how to download a female voice changer and how to set it up?
hello guys is it just impossible to bypass copyright on youtube?
bub
tell me ur pc gpu in #🔍│help-w-okada
prob yes
if you got a copyright claim on your ai cover on yt, you can't do much about it, other than buying a mechanical license and asking for the permission of using that voice
or wait till it gets a strike to your whole channel
or delete it, as making it private doesn't change
Is there a updated svc I can use ?
Can I use a rvc model and inference with svc 4.0
Where can i find Index file in Applio?
@covert lake Where can i find Index file in Applio?
Are you training a model
Last update: Apr 01, 2024
In logs
Thanks
do you know a disconnect prevention method to keep Colab from timing you out for "inactivity"
how do i use it sorry im new
Copy this code to the page Console and press enter.
how do i open page console tough?'
It is only possible on a PC
Right click on website and press inspect and then go to console tab
thank you
Yw ; )
it wont even let me post it due to the song
weights so good youtube think its the real song
😭
@dawn temple do u think u can even legally go against this if weights makes a song similar to the original
Can anyone give me genai project ideas to add more weight on my resume ?
i think i am gigwon
Yo everyone
Hi i've got approx 5-6months to watch this server. Is rvc still the king in ai voice models? Whats the current developement stage?
yeah rvc still is the best
did they change the architecture?
nope
wow...
how is that possible every field is seeing huge upgrades
why is audio so neglactef
rvc has been abandoned by the og devs
they moved to tts instead of sts
im here since day one with snoop thats sad
and Litsa (the best mod here)
is the server like still 70% furry themed?

Ily snoop doggy
crazy
Btw noobies and codename are making an experimental fork
Do we have a good text to speech resource?
is it like a spork
Is there any old Chinese master vm’s 🥲🥲
-hf
- UVR5 UI, by Eddy and Ilaria Huggingface Spaces
- Ilaria RVC Zero, by thestingerx Huggingface Spaces
- RVC⚡ZERO, by r3gm Huggingface Spaces
- Applio, by IA Hispano Huggingface Spaces
A modified version
uhu
hey can someone create a modal for pierre poilievre?
hey can someone create a modal for pierre poilievre?
no
#1159289738314919936 create a post here maybe someone will make it for you
DIlly ding, dilly dong! A new RegalHyperus drum model just released!
I'll Make a Man Out of You (Drum model no. 563)
guys how do i use voice changer?
Imo yes
Welp
What's ur PC GPU Freddy
where do i install the rvc gui
Rvc GUI is an old fork of RVC, don't follow yt tuts
What's ur PC GPU and what are you looking for
3060
Alr, and what do u want to do
just ai covers
is there a new one?
okay thank you for the help.
Yw
@hidden grotto
:wave: @elder willow, How can I help?
Available Commands:
• @weights find <query> or /find <query> - Search for RVC Voice Models
• /create - Create an AI Cover
• /image - Generate an Image
I was doing a bit of research about the various voice conversion libraries - theres a few newer ones like fastSvc, loraSvc, not sure what else. Curious, are any of these similar quality to RVC but with faster training?
Or do any pretrains speed up training?
you should always use a pretrain, original or specific to your desired model, while training rvc model
Hello
people will hear "AI" and start tweaking cus their favorite youtuber told them that it's bad and only bad
Real
Ai has been used in games since forever
DLSS is peak
Guys how do i fix static roboticnessnon the voice changer
Nintendo meat riders when they realize Pokemon used AI for Pokemons. 
Nintendo fans who wanted to have SEX with Nintendo in their ass.
This is more likely a rage bait post, I can feel that.
Normal people probably wouldn't post something like that. 
These are the only images of AI Hub by Weights chan I could find. There are too few images of her besides the AI-generated ones available, even in both AI Hub by Weights server and X account. 

-colab
- Applio, by IA Hispano Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- RVC Mainline, by Hina Google Colab
- AICoverGen-WebUI, by Hina Google Colab
- AICoverGen-NoWebUI [English], by Ardha, fixed by Eddy, Hina and Gdr Google Colab
- AICoverGen-NoWebUI [Spanish], by Eddy, Hina and Gdr Google Colab
- UVR5 NO UI, by Eddy Google Colab
- UVR5 UI, by Eddy Google Colab
- Modified W-Okada's Voice Changer, Google Colab
- FaceFusion UI, by Nick088 Google Colab
- FaceFusion NO UI, by Nick088 Google Colab
- EasyGUI, by Rejekts Google Colab
While the Colab free plan provides up to 12 hours of daily usage, the GPU is typically available for only about 4 hours each day on average.
can someone help me?
when i go to use voice changer i get this
Generated Strengths: for prev:(4096,), for cur:(4096,)
[Voice Changer] Pipeline is not initialized.
[Voice Changer] Waiting generate pipeline...
[Voice Changer] Pipeline is not initialized.
[Voice Changer] Waiting generate pipeline...
[Voice Changer] Pipeline is not initialized.
[Voice Changer] Waiting generate pipeline...
-colab
- Applio, by IA Hispano Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- RVC Mainline, by Hina Google Colab
- AICoverGen-WebUI, by Hina Google Colab
- AICoverGen-NoWebUI [English], by Ardha, fixed by Eddy, Hina and Gdr Google Colab
- AICoverGen-NoWebUI [Spanish], by Eddy, Hina and Gdr Google Colab
- UVR5 NO UI, by Eddy Google Colab
- UVR5 UI, by Eddy Google Colab
- Modified W-Okada's Voice Changer, Google Colab
- FaceFusion UI, by Nick088 Google Colab
- FaceFusion NO UI, by Nick088 Google Colab
- EasyGUI, by Rejekts Google Colab
While the Colab free plan provides up to 12 hours of daily usage, the GPU is typically available for only about 4 hours each day on average.
I AM GIGWON
hi gigwon
i think its a cat
mhm
guys what's the best website/google colab thingy to make ai covers
anyone knows how https://www.youtube.com/@ArtificialShenanigans makes his videos?
-colab
- Applio, by IA Hispano Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- RVC Mainline, by Hina Google Colab
- AICoverGen-WebUI, by Hina Google Colab
- AICoverGen-NoWebUI [English], by Ardha, fixed by Eddy, Hina and Gdr Google Colab
- AICoverGen-NoWebUI [Spanish], by Eddy, Hina and Gdr Google Colab
- UVR5 NO UI, by Eddy Google Colab
- UVR5 UI, by Eddy Google Colab
- Modified W-Okada's Voice Changer, Google Colab
- FaceFusion UI, by Nick088 Google Colab
- FaceFusion NO UI, by Nick088 Google Colab
- EasyGUI, by Rejekts Google Colab
While the Colab free plan provides up to 12 hours of daily usage, the GPU is typically available for only about 4 hours each day on average.
looks like hailuo ai to me
is it free?
i mean do you get some credits daily?
just check
Free or not, you'll have to check it by yourself.
Does anybody have a working catbug voice link 
question what voice changer is free and good to use for laptops or non gaming PCs?
whats your gpu?
how do I check? I got my gaming laptop as a gift
the link in there doesnt work, thats why im asking in here
I'll check later tho
huh
task manager
cant rn
try it
i dont really know how to use it
just search the name
and download the model
I searched the name, where is the download button located, because all i see is create 
iirc the 3 dots
oohh thank you
no prob
Task manager
@hollow tangle Are there any good models that support polish language?
any of em could technically do polish
but you could look for models of polish people anyways
When you say ś,ć,ż or rz in a sentence, vcr does not pronounce it correctly
There were pretty much no Polish models so you are going to have to make your own or request one or pay for one
what to do if your voice burrs
blub
dms lemme show u
if youre looking for a voice changer its simply not possible on your machine
oh
are you sure its a gaming laptop?!??
i mean, integrated graphic card… not a gaming laptop
:(
i can run tf2 better than my old laptop
tf2 is a game from 2008 tho
ik
Who tried to call me in direct message?
Any ai that can take reference images and replicate that art style?
me
Hi, can someone suggest a local model for voice translation, I need that for dubbing the videos. I've searched for web and only found some services, but theirs costs are too high, I'm wondering if there is some local based solution, as I do have a capable gpu.
what gpu?
the only one know that can do that is elevenlabs, but sadly they're on site only
rtx3090
I've tried Camb.ai, but they are also pretty costly
the only way i can think of is to creat a pipeline of whisper, some model that can translate text and tts (and maybe rvc for quality)
Yeah, but if I make this one, then I could turn it into a service like elevenlabs and get money from it, like they do)
if you give whisper audio in english, but ask to transcribe to russian, it will do it
but it does make a lot of mistakes
probably misclick ig xd
the best thing you could do is to transcribe (whisper can do it but not so perfect) and use TTS, don't expect it do 1:1 copy the pitch & intonations but 11labs is the best so far
u mean to subscribe to it lmao
hello
guys my sound is not smooth how can i fix it
i have 4060
is it not enough?
i was using the MMVCServerSIO_win_onnxgpu-cuda_v.1.5.3.18
i deleted it
now i am installing the MMVCServerSIO_win_onnxgpu-cuda_v.1.5.3.16
I'll try it
if it doesn't work properly I'll come back for ur help
also im pretty sure cuda is for amd gpus
uh sorry i thought that here is okada help chat
no it isnt
cuda is for nvidia gpus
he meant zluda
google it
yea i js did
it looks interesting
would this work on okada?
as cuda works better
Applio rvc has zluda support
would it run better than w-okada fork?
it's not realtime voice changer
and does it support all the voice models like the fork?
oh
they need to make one
that way nvidia and amd would be closer in performance
I hope so, though it has rocm support for linux users
Hi
hello
How do I download voice mod?
-rt
Interaction has expired, use the command again for a new interaction.
first link
yes rt
its?
first link
won't open
Guide style is in the same as Blanc_dot's. Thanks Blanc_dot for corrections. Most technical information comes from deiteris.
Last update December 12: NEW UPDATE VERSION b2332
Translations added for:
German: https://rentry.co/ForkVoiceChangerGuide_de
Turkish: https://rentry.co/ForkVoiceChangerGuid...
hey i would like to understand fO method
what do each do?
and how many types are there
does all of them do the same thing?
all of them in fact extract pitch
so for example
if i use crepe
will there be any difference if i used dio,pm and the others?
yes
and also i would like a bit further information about it
because im interested in AI voice models
i would appreciate if you had any more information about it
other then the methods
basically all you need to know is that rmvpe is sota when it comes to quality, speed and accuracy
interesting
thanks john
np
question, will applio's new code fix the spectrogram mirroring from the test version of klm 4.2's pretrain???
(40k)
:3
the mel spec loss function that came with 3.2.8 does help clearing those, but mirroring still happens
unfortunately that's a nature of the upscaling audio by 2x
just bought voices.ai subscription and that probably not the brightest of me 
is w okada the best one to use?
alright
lah akun apcb bisa 30jt
roblox bang 
HAH
ko bisa njirt
beamed
😭
voice.ai? ah the same company who abuses most of their users power usage for distributed training lmfao
Voice.ai allows users to participate in distributed computing to help develop our artificial intelligence models – this has nothing to do with cryptocurrencies, bitcoin or mining. Voluntarily contributed processing is solely used to build voices, train AI models and handle voice processing for other users who have less powerful devices
Source
You just got a crypto-miner-like program on your PC 
Not 100% sure if u want a rich company to abuse for ur pc power, that could cause overheating or issues to u since it happens in background
iirc it happens when you get a model for free, I remember having it myself, they make u have it in the background, and tell u to wait to gain free coins, at the cost of your power
Ofc deleted that shit in a day, like 2 years ago
if you paid, not 100% sure if it does that too, but would you trust a company knowing they do that?
oh yeah i noticed my gpu usage is 100% 😭
Delete that shit RIGHT NOW BRO
😭
don't trust every single youtube tut, there's a shit ton that are sellouts for money or even suggest malware/spyware shit
alright i did
rtx 3050
There's wokada, which uses RVC models in realtime for calls
And there's the wokada deiteris fork, which is basically wokada but has better performance (aka not eating your whole damn pc
)
im downloading that rn
the 50 variants of nvidia's RTX cards are entry-level, which means not the best, but don't worry, it will run fine
-realtime
Interaction has expired, use the command again for a new interaction.
1st link, the wokada deiteris fork, be sure you're using this
for any other issues, @ me in #🔍│help-w-okada
thanks
okay
If I don't reply, well it's 1 am lol

You're welcome
Also I have seen some use operagx too
idk why everytime that someone uses voice.ai, they also have operagx 😭
which is the same company known for spyware in kids smartwatches
Watch out online
holy shit 😭
you don't know the amount of times that non tech people fall for shit like this because that same company does skibidi gaming memes on tiktok
be careful before using smt
wokada is open source unlike voice.ai, meaning anyone can inspect their code and see that it's legit
ah
if u know coding, u can check the wokada deiteris fork here
open source = code is public, everyone can read it to be 100% sure on what they are using
i'm so far from that kind of life i know almost nothing
Idk what job u gonna do, but just warning u to watch out before running a program
things like this are usually hided to the average user, companies use to hide it in the ToS (the thing you accept without reading the 99% of the time)
i’m an architecture student, and yeah i’ll keep that in mind
💀
oh cool, I'm an IT student
yea, sometimes u gotta read it unfortunately 😭
imagine if u didn't join here and stayed a week worried about your GPU always reaching 100% while having just chrome open
😭
fr tysm
yw 
i'm also wondering if codename's applio fork has the same mel spec loss function or not
or new code in general to remove a bit of mirroring of the model trained in klm 4.2.
@weak valley
?
yes, it should use the same
if u cant ask for refund, file a lawsuit against them
oh lol
Uninstall the Voice.ai now. Fork W-Okada is better.
does anybody have a good playboi carti model similar to the voice in timeless ft carti?
To find a voice model, go to #1175430844685484042.
or go to weights.gg and search the model there
anyone know any good men voice ais
If you're looking for some generic voice models here, no.
@solar torrent How can I use weights gg voice over to use when your in a voice channel in discord
What even this Weights.ai website is? Do you mean like Weights.gg or Voice.ai?
i think they mean weights gg
Oops I meant weights gg yeah that
If it's Voice.ai, this site is a scam. If it's Weights.gg, this website is full of voice models there you can use. If you wanna use the voice changer to Discord, you might be looking for W-Okada the realtime voice changer.

the thing is they have wasted money on it
No refund, I suppose. 
there could be mirroring on high notes even with hifigan and refinegan (the latter is not worse), perhaps because of aliasing or something?
that's what it is
Is opera safe or not cus I been using it for months now
no
⣿⣿⣿⣿⣻⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿
⣿⣿⣿⣵⣿⣿⣿⠿⡟⣛⣧⣿⣯⣿⣝⡻⢿⣿⣿⣿⣿⣿⣿⣿
⣿⣿⣿⣿⣿⠋⠁⣴⣶⣿⣿⣿⣿⣿⣿⣿⣦⣍⢿⣿⣿⣿⣿⣿
⣿⣿⣿⣿⢷⠄⣾⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣏⢼⣿⣿⣿⣿
⢹⣿⣿⢻⠎⠔⣛⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⡏⣿⣿⣿⣿
⢸⣿⣿⠇⡶⠄⣿⣿⠿⠟⡛⠛⠻⣿⡿⠿⠿⣿⣗⢣⣿⣿⣿⣿
⠐⣿⣿⡿⣷⣾⣿⣿⣿⣾⣶⣶⣶⣿⣁⣔⣤⣀⣼⢲⣿⣿⣿⣿
⠄⣿⣿⣿⣿⣾⣟⣿⣿⣿⣿⣿⣿⣿⡿⣿⣿⣿⢟⣾⣿⣿⣿⣿
⠄⣟⣿⣿⣿⡷⣿⣿⣿⣿⣿⣮⣽⠛⢻⣽⣿⡇⣾⣿⣿⣿⣿⣿
⠄⢻⣿⣿⣿⡷⠻⢻⡻⣯⣝⢿⣟⣛⣛⣛⠝⢻⣿⣿⣿⣿⣿⣿
⠄⠸⣿⣿⡟⣹⣦⠄⠋⠻⢿⣶⣶⣶⡾⠃⡂⢾⣿⣿⣿⣿⣿⣿
⠄⠄⠟⠋⠄⢻⣿⣧⣲⡀⡀⠄⠉⠱⣠⣾⡇⠄⠉⠛⢿⣿⣿⣿
⠄⠄⠄⠄⠄⠈⣿⣿⣿⣷⣿⣿⢾⣾⣿⣿⣇⠄⠄⠄⠄⠄⠉⠉
⠄⠄⠄⠄⠄⠄⠸⣿⣿⠟⠃⠄⠄⢈⣻⣿⣿⠄⠄⠄⠄⠄⠄⠄
⠄⠄⠄⠄⠄⠄⠄⢿⣿⣾⣷⡄⠄⢾⣿⣿⣿⡄⠄⠄⠄⠄⠄⠄
⠄⠄⠄⠄⠄⠄⠄⠸⣿⣿⣿⠃⠄⠈⢿⣿⣿⠄⠄⠄⠄⠄⠄⠄
idk
how the hell do you have an articuno tf
robotic cat
what bots they got here?
Reply hazy, try again.
[▰▰▰▰▱▱▱▱▱▱] - 47% possible
You may rely on it.
[▰▰▰▰▰▰▰▰▱▱] - 84% possible
Reply hazy, try again.
[▰▰▰▱▱▱▱▱▱▱] - 36% possible
You may rely on it.
[▰▰▰▰▰▰▰▱▱▱] - 71% possible
i don't think it is safe to use opera as it contains spyware (as far as i'm aware) and collects crypto.
as for alternatives i'd recommend firefox
edge
Switch 
I use chrome
chrome my beloved
google still hasnt pulled Honey from Chrome's extentions, tells you everything
What about Honey?
scammed influencers
even with manifest v3 ill stay on chrome
scammed everybody
No adblockers
What does it do exactly
not us italians because it was against the law 😼
steals refererals, made deals with companies to provide no coupons or lower discounts
replaced the links to their affiliate
honey is an extension for coupons basically
Ah
it is a common industry practice that companies pay some percent of purchase back to someone who promoted them, provided a link with a referral code
like give you a link to a gadget on amazon, for next 30 days all your purchases are linked to me and if you buy something amazon gives me a small kickback
honey replaces my referral code with theirs
the idea was simple, you download the extension and they provided the coupons, but they actually took the DEVIL route
guess who are the devs
and lets say a company does promotions and provides 20-30% off coupons, honey made a deal that for a price they do 'we could only find 5% off', that's the best out of there
Mrbeast
What??
money!
and dont forget who PayPal is owned from?
our favourite boy
Elon Muskiedoo
especially elon musk
Don't u use X
bluesky?
@covert lake
-colab
Suggestions for @whole timber
- Applio, by IA Hispano Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- RVC Mainline, by Hina Google Colab
- AICoverGen-WebUI, by Hina Google Colab
- AICoverGen-NoWebUI [English], by Ardha, fixed by Eddy, Hina and Gdr Google Colab
- AICoverGen-NoWebUI [Spanish], by Eddy, Hina and Gdr Google Colab
- UVR5 NO UI, by Eddy Google Colab
- UVR5 UI, by Eddy Google Colab
- Modified W-Okada's Voice Changer, Google Colab
- FaceFusion UI, by Nick088 Google Colab
- FaceFusion NO UI, by Nick088 Google Colab
- EasyGUI, by Rejekts Google Colab
While the Colab free plan provides up to 12 hours of daily usage, the GPU is typically available for only about 4 hours each day on average.
done
to what? what are you trying to do?
also google colab is only for people who have a bad pc, it's cloud
did you check if you got a good pc gpu first ?
nah, my pc is trash atm
AI covers
I want to make a producer tag
You can check your pc gpu via:
ctrl+shift+esc (task manager) -> Performance tab -> GPU
even a gtx 1660 super would be able to do AI Covers
I mean, if you say your pc is trash:
- Cloud (remote good pc, easier and faster than ur PC but it's limited):
- Ilaria RVC Zero: fastest and simplest that you can get for free
- Weights.gg: Partnered with AI Hub, lets u do them easily but u may be in a queue
- Applio Colab: max 4 hours daily, not granted, of GPU
Easiest possible (automatically separates vocals & instrumentals) : weights.gg
easiest cloud: Ilaria rvc zero
Grazie capo
Prego, per problemi, usa #✨│ai-help
I'm romanian, I don't speak Italian but I think I understood what you said
Btw, this technology is named RVC (Retrieval-based-Voice-Conversion), it's Speech To Speech natively, can be technically used for Text To Speech too even if it's not made for that
Oh lol
I said
"You're welcome, for any issues, use #✨│ai-help "
I don't think tts would be more accurate than sts
i mean those are 2 different things, I was just clarifying what the program was
I didn't use it in a while so I don't know how to do it anymore But I'll figure it out 😂
thank you for the links
you're welcome
I can also help you out if you need it in #✨│ai-help
i can help capo
alr
hi
i need help regarding applio TTS, i wanna make a chrome extension and use my pc as server to process the text into speech by selecting the text and play it
do you have any coding skills?
and how do you think you can make an extension 😭😭😭
Is there a particular way that I should be searching for something if I'm looking for voice models that are, on a legal basis, safe to use without running into problems if I used them in a project? I love several of the models I've found here but I don't know the first thing about vetting legality of things. Not that I'm implying or intending to mean that anything here isn't allowed, nor am I asking any questions of ethics.
you need to find models trained with consent from the voice actor
ofc! I am asking if there is any way I could search for those in the #🔍│find-models or a tag I should look for in the #1175430844685484042 channel.
99.9999999% are not what youre looking for, you have to resort to paid ones or be extremely lucky
The majority was without asking for permission, and even if it was, for legal issues I think you would still need to ask the voice owner (actual person) to do what u want to do
Usually it doesn't get taken down for that on YouTube, even if there's a chance
Give me a hint. Where can I find a voice model for Willy Wonka from the 2005 film?
You can search rvc ai voice models at:
- #1175430844685484042
- In #🔍│find-models , Do /find with @hidden grotto
- https://weights.gg/ (login required)
- https://huggingface.co/models (but watch out cus in hugging face there arent only rvc ai voice models)
- https://voice-models.com/
- https://thevoicemodels.com/ (for Turkish Models, login required with discord and level 2 on their server)
if there isnt one, you can:
- #1159289738314919936
- #1191429836321849435
- make it yourself with our docs guides https://docs.ai-hub.wtf/essentials/how-to-make-voice-models/
:wave: @covert lake, How can I help?
Available Commands:
• @weights find <query> or /find <query> - Search for RVC Voice Models
• /create - Create an AI Cover
• /image - Generate an Image
Anyone know where i can find a realistic female voice??
one that doesnt sound like an ai bot
VIETNAM CHAMPIONS ASEAN CUP 2024
DIlly ding, dilly dong! A new RegalHyperus drum model just released!
Rock (Drum model no. 564)
Hello! I am TrynyxAI. Your very own personal asistant! I am here to find other AI such as myself and meet new people!
best model to sound like a girl?
Is anyone talking/thinking about Perceptron? thanks
Langchain: Framework for Building LLMs Applications
https://medium.com/towards-artificial-intelligence/langchain-framework-for-building-llms-applications-bbbabf773dae
There is a app for make faceswap vidéo ?
Which is the best app for AI image generation?
whats your gpu?
what is it
mines 
I do not have a dedicated gpu, I am using integrated graphics
then you cannot do it
locally at least
Can you still suggest
for local?
Both
id say for local ComfyUI if you want Flux, Forge if you want SD 1.5 or XL
Okay
for cloud weights.gg wich uses Flux or Grok wich use a dev version of flux iirc
Thanks
yo
Anyone to make the most realistic voice settings in voice changer client demo
i can help in #🔍│help-w-okada
Bet
you dont need help anymore?
Yeah I do mb I was js eating
okie
hey guy looking for a team to start som new ai
what ai
Forge doesn't support flux?
afaik no
ComfyUI 🔥
im using that rn
ComfyUI is da best fr
idk what to make tho
Post smt on blue sky
LMFAOOOOOOOOOOOOO
i did some days ago and no one noticed
Do it on X
People are already mad about Nintendo using AI
dlss are not "ai" tho
Huh? It uses AI
It uses ai for frame generation, interpolation, and also playing the game on a lower resolution to upscale it on the resolution u want
and wwwwwhats the problem exaclty
people got mad?
People just get mad at everything that uses AI
But honestly this is the best use of AI, you get more performance, which is very needed on a portable console
it's literally a neural network model ("deep learning")
istg im gonna make an ai art profile on twitter
You mean 𝕏??
opened twitter for 2 seconds and all i got was porn
You mean 𝕏??
Imagine Nintendo fans try gaming on PC for the first time. 
im nintendo fans
for sure switch 2 will use DLSS
SteamOS on Nintendo Switch. 🔥
NVIDIA GeForce and RTX (Quadro) GPUs also have DLSS. 
bluesky have dlss
@covert lake why on flux i ask for a girl and i get a KID
also, any way to upscale images?
It needs better prompting 🔥🔥
Dunno on that 
Maybe try searching onljne
I can upscale it for you
Up to 2 Million Pixels
i alr upscale with Forge tbh
Ok
Ilaria upscaler died and idk why
Also you can use models like ESRGAN
I'm coding my own free upscaler API rn.
how
really?
Discord doesnt allow me to Upload it
Its over 10MB
Wait I can just Upload it ob my cdn
*on
fuck discord for this "update"
DAMN
who removed "by civitlai" from your name
I will also Support Videos ig
I did
D:
Since I will rename it
So many users think that it has something to do with civitai
make sense tbh
69!!!
why?
Verified Discord Bots can't be renamed without Discord Support
ohhhhhh
why its not here
enough to be verified tho
Yea its Verified
@hollow tangle
Waiting for the "Discord Experts" to Review my request lol
Thx
yay!
Holy moly I love AI logos
reminds me of something
of what?
idk but i already seen something like this
dam
Does anyone know how to isolate sfx of a song?
how to set up alert system for all crypto coins when they hit 24h low and high and are now on the rise/crash?
these manual price alerts are junk
easy money with 24h alerts buy low sell high
futures trading
who here trades crypto?
no nft bullshit
looking for experienced people 1 year+
uvr
huh
this is not a place for this
whats uvr?
uvr5 is a program to isolate voices or instrumentals
but for sfx maybe rx11 is the best tool, im not truly an expert on sfx
lmfao
!howtoask
How To Troubleshoot 
- Don't simply mention your issue, like "
my rvc is not working". - Describe the step you are on, what you're trying to do, the RVC you're using, a screenshot, etc.
- The more context, the better.
- Don't be desperate. You can ping a Helper, but if they ignore, they aren't available/don't know the answer.
- It's okay if you're frustrated, but don't take it into this server.
- Don't DM without prior consent.
- Don't ask for every little instruction. Put your own effort & test things by yourself.
- Don't ask to ask.
- Check if your answer is a Google search away/on our guides website.
I want to add talking villagers to Minecraft bedrock edition
i dont think this relate to the server
So then what server can help me
the minecraft one(?) idk
You'd wanna use a resource pack and replace all the villager sounds with RVC samples
https://minecraft.wiki/w/Resource_pack
https://learn.microsoft.com/en-us/minecraft/creator/documents/resourcepack?view=minecraft-bedrock-stable
The wiki and this post can help with resource packs. We can't really give much advice for Minecraft tho
if i download a voice model from huggingface, what do i use to open it?
wdym? to get the pth and index?
7zip is an option
yeah i got that, but what i mean is how do i use it
ohh
you need a voice changer or a conversion thing
any reccomendations for a 1st time user?
depends on what you wanna do really
alright so if it's just for personal use?
no ofc, i mean
you wanna change your voice real time?
idk, wouldn't mind either real time or my voice is changed afterwards
try weights.gg
no prob
@ancient swan hey man, curious as it's been a while for me. What's currently the best separation model / arch?
Am a lil confused with all those new releases, betas and so on
Is it still mvsep the king or some uvr released ones?
I think the last time I tested anything ( and quite liked the results ) that was bsrofo xxxx.08
Was there any comparison doc? if so, how reliable it is? how were the tests done? thanks in advance
https://docs.google.com/spreadsheets/d/1pPEJpu4tZjTkjPh_F5YjtIyHq8v0SxLnBydfUBUNlbI/edit?gid=1468543363#gid=1468543363 there is a comparison doc but its for mel roformer models
that's a tough question
So how's the status, band split or mel? which arch so far seems to win?
I need the most reliable arch / model for some very basic anime separation ( probs not a lot of instru / other contamination, maybe even gonna work on 5.1 so very very little contamination
aka, I need least damaging model in terms of spectrum ( aggressiveness wise
if you want to get the most out of the vocals from the song then it's unwa's and becruily's melband finetunes that are trained with emphasis on fullness


AI HUB Docs
