#🧬│ai-chat
1 messages · Page 276 of 1
Hallo
hello dude
Can you please model my voice?ü
😁
Ayo? @oak cobalt level 1 !!! 
I don't know, try asking someone else
Ok .. this groupe is not like midjourney..
we only have gay image generation
You will definitely get what you want, but not now
Ok .. thanks ..
Can you help model my voice?
It was late, so most people were asleep
What sound do you want?
I'm trying to model my own voice but it doesn't work
follow the guides
it's 1:24 am vro ...,
its an international server its sunny somewhere
The program is not working properly and gives an error
Ayo? @brazen rock level 2 !!! 
what error
What sound model do you want?
Ayo? @latent violet level 2 !!! 
So far I haven't found any errors in my model, why is your model having problems?
ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.
google-colab 1.0.0 requires requests==2.31.0, but you have requests 2.32.3 which is incompatible.
What website are you running the model on?
easyguı
I don't know what website it is, if I run the model on the hugging face website
how do i put my own voices
you can send me the link
I'm dealing with it too
Why don't you try it?
Do you want to see?
The edit button
unable to zip
Ayo? @chrome light level 1 !!! 
Of course why not?
tf happened
embed fail happened
I can't post pictures here, just look for the hugging face website
Hello vro.. Kar
ok pro
hugging face website email verification says insufficient token

yo
eyy
anyone know if theres a rvc model of Alcina Dimitrescu or a voice similar? cant think of one or see one 😦
ppl does anyone knows a free ai that i can paste a description of a story to and it can write a whole book about 100 pages?
What chunk size and extra should i choose for 1080ti 11 gb graphics card
Are you guys using that voice changer
-docs
Suggestions for @elder willow
- How to use RVC Mainline Colab by Cauthess
- Full AI Voice Model Training Guide (local) by Christopher Villanueva
- AICoverGen Colab Guide by Eddy (Spanish Helper)
- Create a model with RVC disconnected (colab) by Angetyde
Noooo
ok wow thats just incredibbbel
Hi!!
I know very little about this but, it is possible to make ai covers in mobile with this models?
Project Strawberry is exciting
Tg6#rFp2&d!lZ8s@W1%qG9hP0zK!oH3iB4$cV7
цепЩШETGIWIT(W)#t0weitwe9tik9swoetfgikwsoetgfwskitgostg
Ilaria RVC
You can start with any voice you want a model of.
Actually depending on the source you'll use to make a model, you can isolate audio/or acapella if you wanna make a singer model with BS Roformer.
Or Bandit Plus/Bandit V2 if it's a speech
also, go to the #✨│ai-help for more info if you got more questions.
wait wait i think you dont understand me
i want to remove vocal from song using UVR5
Use BS Roformer on MVSEP.
That's it.
is that a new program?
Nope, it's a page.
This interaction has expired, use the command
/guides realtimeif you wish to see it again.
There you got the guides.
Thanks
Meen
If you got any other questions, go to the #✨│ai-help channel and ask there
taking ages till i get the file
there is option to download th bs thing to the uvr5?
There is a beta update for UVR that allows usage of BS Roformer models.
I don't have the download link sadly.
yea im downloading
it is same as the site right?
its removing noise and all the stuff?
or should i apply more models?
Nope, the BS Roformer models available when updating UVR with that beta update got 10.80+ of SDR.
Tho i still recommend them.
i dont have any clue what you just wrote
Ayo? @fathom flax level 2 !!! 
but ok
I'm not sure.
Yep, what Ilaria said.
Do you guys know any AI able to accurately edit images?
https://www.youtube.com/watch?v=mpLeSzLlSls does anyone know how they did this (spongebob Video Theme)
Ayo? @harsh furnace level 1 !!! 
does anyone know????
Someone Goose goose duck? WGCQESP
Hello
There is a pipe bomb in my mailbox 
Hi guys
hi
Ask for help in #✨│ai-help or #1192011222023950368
Hi
Hii
hello guys help me please i need best version for my rtx3070ti and ryzen 7 7700
How to make villagers talk?
Check https://docs.aihub.wtf/, you can use either applio or mainline locally
I think what you want is Text To Speech (TTS), RVC forks such as ilaria rvc mainline & applio have built in tts (using Microsoft Edge TTS to make a generated tts audio, which i suggest you to choose a tts model that is the same gender and language of the rvc model you wanna use, and then convert it with rvc)
NOTE: RVC isn't as good as GPT So Vits for tts, but gpt so vits can't use rvc models (and viceversa), and its only limited to: english, chinese & japanese, if you wanna check gpt so vits instead, read https://docs.aihub.wtf/tts/gpt-sovits/
If you wanna do tts locally (if you got a good pc):
If you don't got a good pc you can do it online:
-
Ilaria RVC Zero (Running on A100 GPU, free fasted rvc on cloud) and the guide
-
Use Applio UI Colab (with google colab T4 free daily limit gpu)
-
if you don't wanna use edge tts, you could try another tts ai from [our tts index](https://docs.google.com/document/d/12hCYJqNCFl6jWKoVvCxtwt2V6nSoilgi5La8dkZa1KY/edit] and use the output as an input in rvc
yes
anyone know how to do live audio for models
Realtime voice changer for calls?
Check below
-rt
This interaction has expired, use the command
/guides realtimeif you wish to see it again.
Use wokada, if you got a good PC do it locally, else use the colab
thanks
Your welcome
🎙️ Realtime Voice Changer (Local)
,wk
Ayo? @elder willow level 2 !!! 
1. Zonery - 380 plays
2. 𝚁𝚎𝚝𝚛0𝙱𝚛𝚒𝚐𝚑𝚝 - 13 plays
3. snoptebo - 9 plays
4. DapperDuck - 8 plays
5. kelvin - 6 plays
6. the jaguar𓂀 - 5 plays
7. jensyao - 3 plays
8. Dep C-137 - 3 plays
9. liquidjett - 2 plays
10. Morgan - 2 plays
11. DF8 - 2 plays
12. Nippy - 2 plays
13. Dziber - 1 play
14. Evannith - 1 play
1. Zonery - 443 plays
2. kelvin - 5 plays
3. 𝚁𝚎𝚝𝚛0𝙱𝚛𝚒𝚐𝚑𝚝 - 4 plays
4. DF8 - 3 plays
5. Dep C-137 - 2 plays
6. anita motomami max wynn - 1 play
7. Lorelesme - 1 play
apparently 3060 & 3070ti ain't good enough
I don't really use it locally but that should be good with the right settings
They are
oh
Can I get ai pics here?
go there if you need help #🔍│help-ai-art
Ok
You can use dall-e 3 (same one of chatgpt plus) for free by @elder willow in #🤖│bots , or also for more customization and knowledge of other open source AIS like stable diffusion ask in #🔍│help-ai-art
1. Matn - 122 plays
2. PotatoCat - 73 plays
3. Flyken - 68 plays
4. 5b - 54 plays
5. chef - 37 plays
6. tëa - 32 plays
7. TORONTOS FIRST LADY - 25 plays
8. cad - 23 plays
9. da-ta - 16 plays
10. I’m really feeling it! - 10 plays
11. apollw ✿ - 9 plays
12. KanekiKen - 9 plays
13. yuko - 8 plays
14. MysticalWaldemar65 - 8 plays
73. Zonery - 0 plays
Damn lol
👍
can someone help me omg
yeah i got it just needed to fix the chunk setting
Is there any better ai or is that the best for creating images?
Don’t ask to ask, just ask
Stable diffusion if you learn how to use it correctly
?
Is it hard?
Ayo? @elder willow level 1 !!! 
;-;
Ayo? @sonic wren level 1 !!! 
this tutorial : https://youtu.be/VSXwS_5wnlw?si=DrPewYGVa58Jcpx2
That colab is very outdated
I recommend to use Ilaria RVC Zero on HuggingFace instead
Table Of Contents Introduction Model Loader (Download & Upload) Inference (use RVC AI Voice Models) Ilaria TTS Settings (Inference) Introduction Ilaria RVC Zero, is an RVC (Retrieval-based Voice Conversion) Fork made by Ilaria & mikus, running only on Hugging Face Spaces, it’s called this way...
Ilaria RVC is a fork of RVC that works on HuggingFace for fast and free conversion
The google colab that the video linked doesn’t work anymore
Takes less then a minute to make
Applio is basically just RVC but with different ui
Applio will sound the same if your using the same settings
Is that the best one?
Yeah basically
Is it a bot in this server?
Haven’t really tested it
If you want it generate good photos with stable diffusion you have to do lots of tinkering
what do i do if the voice model i want is not there?
Like installing the right models, loras, finding a good negative and positive prompt
it's working tho thanks!! ❤️
Check weights gg if they have the model
Ok where can i find?
Ask in #🔍│help-ai-art
what is this??😭
Okay
Website that has a bunch of RVC models
Read the guide I sent
thanks!!!
Table Of Contents Introduction Model Loader (Download & Upload) Inference (use RVC AI Voice Models) Ilaria TTS Settings (Inference) Introduction Ilaria RVC Zero, is an RVC (Retrieval-based Voice Conversion) Fork made by Ilaria & mikus, running only on Hugging Face Spaces, it’s called this way...
Civit ai to whatever it’s called
Where can i find
Website
You can get support with it in #🔍│help-ai-art
Is chat gpt one the best one i can message in discord?
Yeah
But quality would be iffy
There is a local version of SD on iOS called draw things you can test out, it has Lora and custom model support, here’s some boykissers I generated with it
🐈
I use 0.66
Do you guys know any unlicensed high quality (with proper accentuation) English model for book voiceover?
Ayo? @carmine prawn level 3 !!! 
No
is there a way to do 'logical ands' in the search of #voice-models?
I generated those using the Boykisser Lora from #1159496755218501692
I generated those using Draw Things which is a local SD client for iOS
Tho any sd program that can load custom models and loras can work
@elder willow
Do I have to ask it in #1192011222023950368 ?
Then i can, but i want to know if I'm going to get any help 😄.
Hi!nice to meet yall
If you need any help ask in the #🔍│help-ai-art channel
Ilaria TTS has nice models, but I wonder if they are free(unlicensed) to use?
Ilaria tts is edgetts
So you would have to view whatever that license is
Well I'd like to go for Google tts then 😅
Thanks for the response
Ayo? @elder willow level 6 !!! 
hey i just found out about this threw a yt video how do we get the voices to work i want to play around with jschlatt?
yo which one do i get for nvidia
Ayo? @civic pumice level 1 !!! 
is it only me where rvc cracks when i say the letter s 😭 im starting to worry that i pronounce s weirdly
an1 know how to fix realtime voice changer, i cant hear my mic
help wait am i confusind rvc and okada im slow]
can u send a ss of ur audio devices?
like u have ur mic and headset in the right places?
yeah hol on
Ayo? @summer spear level 1 !!! 
meow
dms
Monitor on w-okada should be your speakers/headphones

he has that
im helping him bc i had the same issues hes having 😭
Hey
meow !!
hi
Where is the members list on mobile?
discord updated theres a search bar thing at the top now
Only an hour this server's officially a member whore
meow meow
meow? meow meow, meow!
I'm afraid the meowing won't save you this time
scared meow
The Koreans have lost faith in an American-led NATO and they're moving toward their own devices.
yes, cats.
So if they won't believe in us, then we shouldn't believe in them.
meow!
whats RVC
realtime voice changer
RVC, which stands for Retrieval based Voice Conversion is a open source AI software used primarily in gradio to convert audio of one person/character to another
trying to explain it in a way they'll actually understand
😭 not everyone is a nerd like us yk
Which is compatible with RVC models
pytorch models. actually
whats the difference between RVC and without rvc?
No only RVC models or whatever else w-okada supports. PyTorch isn’t just for voice
And w-okada works with RVC models in onnx too
Except AMD users because no Cuda
(Unless they use the voice changer fork)
amd can use their own version of trt
there are githubs with it
bro i swear this realtime voice changer shit is gonna make me explode
need help?
What is the best free ai song extender?
Give context and say what you need help with
its not that hard to read the guide
And can we give timbovill and MrM0dz a round of applause for being such great staff please
w
como me postulo actriz porno reis?
Hello I'm Jess !
I love the digital world and I'm realy interested to learn new things all the time. I'm into the IA world of possibilities and I'm really happy to have joined this server
Does anyone still use kits.ai for their AI models or no?
If yes, damn you can pay that?
If no, I'll accept it.
hii
Can somebody make some weeknd remixes of the songs he did for take care
anyone knows what happened to the previous ai hub?
whats the official download website
anyone have any recommendations for a good vocal remover, vocalremover.org isnt cuttin it sometimes
Hi
hi
hi
Hi
Ayo? @elder willow level 1 !!! 
Hi
Hello
Hello everyone, I have a question, I made my model and I want her to sing not a cover but her own tex. How do I do this?
IM ONLY survivor
This is the deadest chat of the deaders chats of deads of chats i've witnessed 
Hm, wanna chat?
can someone make me a data set model pls its too confusing
hola mi amor ❤️
Hola ❤️
Como estas mi amor ❤️
where do i get the rcv?
really?
Sure just DM me..
everyone is very nervous hahaha jst kidding mate.
hello, i need help
when I install MMVC, I just have a white screen, what should I do?
Nervous?
You just dm me.
Hey
no me
Just dm me
-colab
- Applio, by IA Hispano Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- RVC Mainline, by Hina Google Colab
- AICoverGen-WebUI, modded by Hina Google Colab
- AICoverGen-NoWebUI [English], by Ardha, fixed by Eddy, Hina and Gdr Google Colab
- AICoverGen-NoWebUI [Spanish], credits to Eddy, Hina and Gdr for translating and fixing Google Colab
- Ilaria RVC, by thestingerx Google Colab
- EasyGUI, by rejects Google Colab
- UVR5 NO UI for Google Colab, by Eddy Google Colab
- 🆕 UVR5 UI, by Eddy Google Colab
Ayo? @elder willow level 2 !!! 
does anyone know how to export in mono on. Rx 11
it's rather outdated and you shouldn't waste your money on it, so I'd recommend this https://github.com/deiteris/voice-changer
theres amd stuff on the windows, i have a nvidia graphics card, will it still work?
can someone help me setting up the real time ai voice changer?
Ayo? @cosmic cove level 1 !!! 
hello guys, how can i download Tensorboard local?
sa guys
Where I can find dvd ripped shows ?
Ayo? @cinder kestrel level 4 !!! 
i wanna train a 40min dataset on weights but this keeps popping up when i upload: ! some files were rejected. please check the file type and size
yeah it doesn't allow that length, if you wish try following colab spaces (one of the first three)
-colab
- Applio, by IA Hispano Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- RVC Mainline, by Hina Google Colab
- AICoverGen-WebUI, modded by Hina Google Colab
- AICoverGen-NoWebUI [English], by Ardha, fixed by Eddy, Hina and Gdr Google Colab
- AICoverGen-NoWebUI [Spanish], credits to Eddy, Hina and Gdr for translating and fixing Google Colab
- Ilaria RVC, by thestingerx Google Colab
- EasyGUI, by rejects Google Colab
- UVR5 NO UI for Google Colab, by Eddy Google Colab
- 🆕 UVR5 UI, by Eddy Google Colab
why train on weights
???
i dont understand why is my speech stupid
you not making sense
your crazy
what
Explain to MOST dumb person like me, how to clean up dataset? I tried through Audacity and once again trained model, but it's still has SO many artifacts :(
where you get your audios from?
Right from the game
Program... It's a program, Meta
Ayo? @arctic tiger level 5 !!! 
dont talk to him hes trolling
Audacity is also on PC
Wait, really?
do you use izotope? aihub guide shows you how and every model maker use it
just look at his previous messages
No, I use Audacity with all the standard plugins, including Noise Gate
stop
my pc is shit
collab dont require good pc config

i wasted all my gpus on colab bro
i dont want to spend money either
What is the best tool to cover ia on your cell phone?
just use another account
weights.gg its pretty easy and can do the job
@arctic tiger you dont like weights.gg?
yeah it's 4 hour free daily limit
yea
you can wait till tomorrow or use another google account if you wish to resume
^
how do i downlload the rvc
Hi! When I talk, my AI lisps and burrs “sh” and “r”.
I'm using "w okada voicechanger"
Video card: 3060 RTX
Also using RVC model
Tell me what could be the problem? Maybe RVC not best solution for now? Or it isn't RVC and just a Model issue? Or maybe RVC or "w okada" pretty old and now is there anything better for talking live? (I expect quality as ElevenLabs AI)
also could be your voice changer setting or model itself
Sorry for maybe offtop, is RVC best models for now? Or maybe now is there something better then RVC?
Ayo? @rose glen level 1 !!! 
not quite sure about that since i only ever used rvc for my ai voices
Hello
hello
¿Alguien sabe cómo autotune las voces?
what is a good local TTS option ?
idk da faq u doin in ai hub

You're an AI fan
yo
there's a model I like of RVC, but for some reason it's not on weights, can I post it?
@pale patrol I have information in verified VC for you
We ask you only post your own models to this server. I'm unsure on weight's policy tho
yeah but give credits to original creator if possible
thats how id do it at least
posting a model someone else made is iffy
it was deleted for some reason
or remake the model, perhaps
OHHHHH
I JUST REMEMBERED
IT WAS IN THE OLD SERVER
but we backed up the old server models on weights gg tho
I found the original
ah
I am new here.
Welcome
no I said there was an error importing it when it was getting backup'd
posting someone else's models can be considered as stealing
Ayo? @lethal flax level 5 !!! 
Who are you and how do you have AI masters without the lower level roles
There's paid ai voice software. Currently rvc and diffsinger are the best free open source methods
Vote Booster: Vote now for a 10% boost. https://arcane.bot/vote
✨ Tip: Use /card to modify your rank card
alright
Tea accidentally created 2 Max 2 voice chats lul
now if you guys will excuse me
what kinda server is this broo
Chaos
AI voice server plus rapid shitposts
I gotta go and extract every line from 2 seasons worth of a show
looking like it
Ai vocaloid servers are a lot nicer
the last part is true

I don't even know why I joined this
Ayo? @balmy pollen level 1 !!! 
pretty fast
https://fxtwitter.com/vocaloid_beta/status/1813815973004099876
Vocaloid 6 ai is getting a major update. And with vocolochanger feature it can accomplish the same results as rvc
【ご報告】
VOCALOID β-STUDIO期間中は皆様のご協力をいただき、本当にありがとうございました。
本日をもって本アカウントの運用はクローズし、今後の告知・活動報告は @vocaloid_yamaha から発信いたします。
最後に、皆様へのお知らせがあります。ぜひ動画をご覧ください。
can we train ai voices locally with amd rx 6800?
No because it’s AMD unless Linux + rocm
no, unless you use linux and rocm

what about rtx 4060?, i only have that gpu
You can
ye
are you kidding me right now
does training rtx 4060 will produce the same quality as tesla t4 colab? because 4060 only has 8gb vram.
I just put tons of lines from the character I'm trying to train and nothing
The ninth circle of hell
@forest quarry scam
The scam wasn’t even set up correctly
Might just be a logger then
guys how I make high quality datasets? like how do I remove the reverb effects of vocals for example
Hi
use stuff like FoxJoy Reverb Removal on MVSep
btw, create an account
i didnt log in cause im lazy :(
👌
either of following:
- UVR deecho derverb
- foxjoy dereverb (doesn't work on mono reverb)
- clarity VX dereverb pro plugin
More info: https://rentry.co/RVC-dataset-RX11#best-model-for-dereverb-and-de-echo
^ yea this as well
alr tysm
Once again, sorry if I use not right chat to ask, but... Which pretrain is better (Ov2Super, RIN_E3, TITAN-Medium, Snowie + RIN_E3)?
Hello, I think I want some suggestion about text to speech the markdown format text. But there is a lot of model that will find the markdown as illegal token. Thus I have used the "markdown-to-text" and use regex. Here are some code I written in TypeScript. Wanna get some sharing in experience about convert markdown to normal sentence. Basically the model framework I am using is GPT-SoVits.
import removeMarkdown from 'markdown-to-text';
abstract class AbstractVoiceService implements VoiceService {
/**
* Removes code references from the given text.
* @param text - The text to remove code references from.
*/
protected removeCodeReferences(text: string): string {
return text.replace(someRegrexToDoThatButDiscordCantDisplay, '');
}
/**
* Preprocesses the given text to remove unnecessary characters.
* @param text - The text to preprocess.
*/
protected preprocessText(text: string): string {
text = text.replace(/^([*-+]\s.*?)([.!?。!?]?)$/gm, (match, p1, p2) => {
return p2 ? match : p1 + '.';
});
return removeMarkdown(text);
}
public async textToVoice(text: string): Promise<void> {
this.shouldStopPlayback = false;
return new Promise<void>((resolve, reject) => {
const removeCodeReferencesText = this.removeCodeReferences(text);
const preprocessedText = this.preprocessText(removeCodeReferencesText);
const textChunks = this.splitTextIntoChunks(preprocessedText);
this.textToVoiceQueue.push(...textChunks);
this.processTextToVoiceQueue()
.then(() => {
const interval = setInterval(() => {
if (!this.isTextToVoiceProcessing && !this.isVoicePlaying) {
clearInterval(interval);
resolve();
}
}, 100);
})
.catch(reject);
});
}
}
Mejor usa Auphonic.com con el presents de Remover music es muy buena
What differnce betwen D file and G file?
And what's better for speech? crepe or rmvpe? 
In the colab you put that 2 and in the pretrain you put it
There seems to be no difference.
RMVPE
Ayo? @empty willow level 1 !!! 

Rmvpe
why my gpu is not detected ? btw my gpu is amd rx 6500 xt , anyone can help ?
That’s only if your using crepe
Are you trying to use the voice changer?
sure , can u help me ?
Ayo? @worldly egret level 1 !!! 
Yeah
Are you trying or make covers or use the voice changer in real time
what should i do for the first which file must to download?
for streaming on tiktok
Nah
On yours going to want to use the w-Okada fork since your on AMD
lemme get the link
Download the one that ends in .dml
can i dm u for ask with picture ?
You can send media in #🔍│help-w-okada
any1 know how much training data you need to develop a fairly accurate human model
for RVC, id say 10 mins is already good
oh tysm
Ayo? @raw tartan level 1 !!! 
Hey Peeps! Any recommendations for Free Vocal Removing Programs? All of the places I was using have hacked up the prices extortionately
Ayo? @dense lotus level 1 !!! 
has anyone tried to use the category encoders module (python)
for some reason I can import but not actually use the module.
Ayo? @dense oasis level 1 !!! 
.
i'm lowkey tong xing lian 🙏🙏
Hi, I have a question is AI song generation completely free, or do you have to pay for it later? Sorry for asking, but I'm new and a bit confused.
on what service
AI generated covers
Ayo? @void cosmos level 1 !!! 
okay but what are you using
Category "models" and a bot for generating covers, I don't remember which one.
oh that thing
Excuse me, do you know if the Rx 6600 is compatible with the mmvc program?
okada?if yes, yes there is a version of okada for amd
my virtual audio cable how do i fix it from sounding distorted like its cracking and has alot of static
It is the first time I install the program but my graph does not appear, only cpu
virtual cable probably messed up, use VAC lite instead (if you aren't yet)
https://software.muzychenko.net/freeware/vac470lite.zip
extract, open setup64, install, use as output in okada and input elsewhere
thank u
yw :)
you got the wrong version for your GPU
honestly, for AMD stuff, I'd recommend using Emojikage's fork for Okada...
https://github.com/deiteris/voice-changer
read the readme, download the amd64 dml zips, use it and have fun
リアルタイムボイスチェンジャー Realtime Voice Changer. Contribute to deiteris/voice-changer development by creating an account on GitHub.
ok ty
Ayo? @heady pond level 1 !!! 
hi
can i make a model with the a free account or do i have to pay?
you're welcome btw :)
where? if we're talking about weights.gg yeah no more free training
hello chat..
ello
damn
any anyone train a model for me?pls
you can just #1159289738314919936
or learn how to do it in colab
Last update: Mar 8, 2024
Hi
yo, does anyone know how to make text to speech with voice model?
this feels like an ice spice song
https://www.youtube.com/watch?v=EHBv-qqtj-E
there isn't a native way to do it with RVC but you can just generate TTS elsewhere and convert with RVC
oh, ok. Thanks for answer
You're welcome :)
Table Of Contents Introduction Model Loader (Download & Upload) Inference (use RVC AI Voice Models) Ilaria TTS Settings (Inference) Introduction Ilaria RVC Zero, is an RVC (Retrieval-based Voice Conversion) Fork made by Ilaria & mikus, running only on Hugging Face Spaces, it’s called this way...
for weights not anymore unless u use referal code, else u can learn how to use google colab https://docs.aihub.wtf
Last update: Mar 10, 2024
Thank you very much!
no problem
https://drop.com/buy/piifox-binary-asa-profile-keycap-set
yo these keycaps are sick
check them out if you need keycaps, i just ordered some for myself
only 2 days left to order them
Hello everyone 👋
yo hi everyone!
promo only in #1159290752195633273
Hi
Ayo? @prime hill level 2 !!! 
bro what did i do
why he saying fuck me
im used to civitai generation but messing with automatic1111 is really fun so far
where can i find like a tutorial channel or smth
Table Of Contents Introduction Model Loader (Download & Upload) Inference (use RVC AI Voice Models) Ilaria TTS Settings (Inference) Introduction Ilaria RVC Zero, is an RVC (Retrieval-based Voice Conversion) Fork made by Ilaria & mikus, running only on Hugging Face Spaces, it’s called this way...
ok ty
Re-inventing the wheel.
Product is not useful for AI development. :)
- uses hugging faces
- does not include architecture agnostics
- does not emulate neuro transmitters or neuroreceptors of the brain
- requires too much data
- adds bloatware for something boiler plate
- does not include offline integration for python programming or otherwise
🤣
🤣
that does nothing to invalidate what was said, so :)
nono its just funny
Are you stupid or are you stupid
you wish :)
The product is designed by to make the access of the software easier
It isn’t meant for development because of its licence
by providing no integration, right. :)
then it is useless for AI development.
It isn’t designed for integration
that's what makes it useless.
meaning, no, it isn't meant to make software easier.
It’s a fork designed for that piece of software to be easier
with no integrations making it harder to use. :)
If the person wanted integration the person would just check out the main branch
that's not how that works.
Secondly, no.
I've built MAML parts and tooled one GPT replica by hand before.
And what does that have to do with this?
the tool recommended is not of use to integrate into any AI model. :)
Including data gotten from it.
The interface type does not matter.
https://docs.google.com/document/d/1YbXcLFPaGjhOdG5NFkK3QrucCEpHZBwFUxkeMO8aB18/edit
The listed tool is not good enough to use for AI development or integration.
All the main branch will tell me is the type of code one can imitate.
Because it isn’t intended for such…
you're missing the point
and you're welcome to pull your punches more with that bunting the bullet.
Do you know the targeted audience for the tool even listed?
Yes, and that's an example of bunting the bullet I was talking about.
You're doing it for validity and I'm not going to entertain this game of yours further.
deflection and derailment like that will equally not help you make your point.
Have a good day. You'll look for anything to deflect.
Tryna be last?
Does anyone know how ppl make 3d ai covers
The last message
no, but gpt-4o might.
Ayo? @left rampart level 5 !!! 
gemini is recommended
You kept on deleting your message and replying the same thing after I saw
about?
and? You're welcome to keep pulling your punches.
and that makes me assume you are trying to be the last message in this argument
To seem like you won
you had nothing burger to argue and kept flailing.
taking a pic does nothing. so. you're welcome to keep intimidation attempts going before I block you.
Shows your editing your messages to make what I’m saying invalidate yourself
Just mad because you can’t push a pull request and be added to the list on contributors
bro sounds like one of those stereotypical snobs that think they're better than everyone ☠️ even the PFP fits
sure dude, if you say so.
mhm.
Imma get an admin rq
okay :)
They are laughing in a different server already
@wooden jolt troll spotted
what
he’s not a troll he just wants to be right
yah idk either man
"mmhmm I'm better than everyone because I edit my messages when someone invalidates my opinion"
that's hilarious
and?
hilarious that it’s true
@timid musk
quick to anger yourself, ey?
“Ermmm actually and?”
I mean
“And yap yap yap”
this person is not good so they should be banned
They haven’t done anything for months here
I think this user is a bot tbh
Proving my point.
your delusional.
with the purpose of rofl reacting people
NOT HIM DELETING IT ONCE YOUR POINT WAS PROVEN 😭
sounds pretty delusional of you to assume, ya
Attempted to delete to look better
Ayo? @storm meadow level 105 !!! 
"oh no, self moderation"
"what ever wilst thy inner butler do"
The admins would find this hilarous.
literally me
practically how it spirals
why are yall even arguing
they disliked product review
dylan is mad because he wants to be right
thinks he's always right
well, we agree to disagree
"right to be wrong"
and rofl reacts people when he they have a point
mhm.
keep pin wheeling.
Nice server mutuals
and?
and?
for someone saying that it’s kinda weird for you to edit that message multiple times
uh huh.
keep pin wheeling.
"and?" - the guy who only says and, and uh huh, and speaks like a victorian child, and uses terms that nobody uses in 2024
right....
this kid bruh
your point is.
and "right..."
ditto?
and "your point is?"
ok
ditto?
@left rampart mate if u r wrong just admit
Same thing
easiest thing to do
how do you know what "keep pinwheeling" means but not "ditto"
same thing
real
how do you know what "keep pinwheeling" means but not "ditto"
just let them flail.
yep this guy's an AI
ilaria rvc exist for people who cant afford a pc powerful enough to run it locally or just dont wont be bothered with installation, it uses an A100 80GB and its fine like this, now drop the convo
No but he’s as smart as googles
does it use numpy?
difference between what? you and someone who admits they were wrong?

I know how to pee passed human+AI tests.
difference between what? you and someone who admits they were wrong?
💀
i said drop the convo, im not here to argue.
the program is "as is" you like it or not.
have fun and a nice day.
I'm wrong
It’s a fork of RVC and uses PyTorch models as it’s format
they asked you to stop, bro
I’m answering your question
Not trying to extend the argument
see, now he doesn't repeat!
doesn't matter. Its dev said halt.
i can see the edited and deleted messages @left rampart
its in promo
YOOOO IT'S AN ADMIN
sameee :3
yeah, and?
imma put all you turkies in timeout if you dont stop being a bunch of gobblers
everyone make up
ok good
L troll cant lie
i will return to my kitchen now and makea da meeatballz
ooow, noice
sorry I was kinda a jerk
heat of the moment.
just don't let it go all to your head, ey?
And the rest be none the wiser to it ;)
if you'd like, take a poke at https://hub.docker.com/r/de3343/ai_mods_py3.10 & pybrain3.
This is some of the code I am testing.
if you need pybrain3 documentation https://web.archive.org/web/20230115194351/http://pybrain.org/pages/home
The simplest thing I can do is enable the curious.
and of course, god speed.
Is there a website or app where I can input 2 snippets of a song, and it will make them transition to eachother with ai?
d
Mix.ai doesn't exist, Lalal ai doesn't do that, audiobridge doesn't exist, endless AI is to broad of a search, and auphonic is for podcasts
anyone know any guides for training tts voice model, that include everything from a to z? I've been searching for a comprehensive guide, but basically everything I've found either doesn't explain like 70% of stuff happening, or requires some pre-existing stuff that's not explained either
@lethal flax these may work better and closer to what you were looking for
Ayo? @crimson hull level 1 !!! 
it's a means test..
What they're looking to filter for is spanish speakers from non-spanish speakers.
Anyone know how to specify which cuda device applio uses
Cause I have a 3070ti and a 3060 but the 3070ti has less vram
bro
you didnt understand it did you
"english or spanish"
why so little kits ai models
Ayo? @elder willow level 1 !!! 
there used to be more
why the fuck you needs kids models
SORRY
I READ IT WRONG
I APOLOGISE
does anyone know how to extend songs with suno it doesn’t give me proper results when I ask to extend a song it gives me a whole different genre
wierdo

Because kits ai removed the community tab
and they can't be downloaded locally, as I know so far
how do you extend songs with ai I’m gonna actually lose it if I can’t figure it out
Ayo? @frank kiln level 1 !!! 
suno does it iirc
you should rered the response you've over-reacted to if that's your take away :)
Ayo? @left rampart level 6 !!! 
Not a lot of people develop such themselves or uncertainty perhaps.
kits is dead?
also I have an idea for a process to create songs with udio and use rvc for custom models unless anyone has better solution
possibly create the voice realtime
use only #1159290752195633273
what
hello
Always has been
uses hugging faces
Literally the biggest platform for AI
does not include architecture agnostics
Its a tool designed only for inference of ai covers and tts
requires too much data
what
adds bloatware for something boiler plate
The TTS? That's literally what people want, its a fork
does not include offline integration for python programming or otherwise
OFC, it's just a fork meant to be used for the ZeroGPU (A100, 69gb of ram) given by Hugging Face for fast free cloud inference,
Also its not an API or smt
kits.ai is greedy, use rvc that is free instead
why 4 pings
eleven 11, descript, gpt chatting with itself using tts wav & video samples, loop with python selenium
simpler solution, make gpt chat with itself at 2 chat bots.
Hi everyone, how much "Batch size per GPU:" should I set in the RVC WEB GUI to train a voice model on an RTX 3060 GPU with 12GB VRAM?
ni##@
Ayo? @finite fog level 1 !!! 
wtf is UpdatePresence and why does this script want access to it
Ayo? @unique cosmos level 1 !!! 
it wants discord to be open
hi
i need a younge sheldon one
real
Can you create a song with text
Is there a website or app where I can input 2 snippets of a song, and it will make them transition to eachother with ai?
Like adds ai generated stuff between
suno maybe
it won't work with copyright stuff

Yo does anyone make tiktok or yt vids?
Ayo? @elder willow level 2 !!! 
what
hi
any good ai's that upscale vids?
I'm a new member I want to clone my voice to use with RVC-Gui
can someone teach me?
Anyone have decent knowledge of the latest generative video tools/methods? I came across a video, and it's quite obviously AT LEAST a face swap, but the quality is insane, trying to find out more about the topic.
Don't wanna post in general because it's propaganda, but I'm happy to share if you hit me up.
RVC-GUI is outdated
-local
- 🍏 Applio, by IA Hispano GitHub
- Mangio-RVC-Fork, by Mangio621 Huggingface
- RVC Studio, by SayanoAI Huggingface
- AICoverGen, by SociallyIneptWeeb GitHub
- Replay, by Replay Team Website
- Original RVC, by the RVC-Project team GitHub
- GPT-SoVITS, by RVC-Boss GitHub
Credits to Faze Masta and Antasma for compiling these links.
I personally use original RVC
Facefusion for face swaps
Anyone know any good video ai upscalers to use?
@not everyone
.
corndog
hello

Yo does this AI voice work on roblox?
Test
Hello

:l
Ayo? @grim glen level 1 !!! 
I can’t fall asleep bruh
tf you saying, listen all that happened is in a survey they asked if i speak english or spanish more in the household, where it sounded too close to the "english or spanish meme" so i thought its funny, but YOU thought i didnt understand what the question was and decided to EXPLAIN* what the fucking quesiton was to me, so how do you want me to respond to you?
Hi, you guys know how to fix a CUDA error during index extraction in model training in mangio rvc? This is the first time it happens to me
Hi
Ty!
Ayo? @fossil plinth level 1 !!! 
Hello
hi
Damn.. I was wondering why most of Shyelijah's stuff had been removed
And the fact that they hired Niosi is absolutely disrespectful
Hello
for deepfake use https://discord.com/channels/1159260121998827560/1163571683848900629
the realtime voice changer wokada could, i dont really use it tho, you could ask in #🔍│help-w-okada or #1192011222023950368 , also the guide is below
-rt
This interaction has expired, use the command
/guides realtimeif you wish to see it again.
wdym 'hindi ai bots' ? u wanna make an ai cover? if so, you can either use the discord bot weights or astra labs in #🤖│bots (if u wanna do it by discord bots)
@bleak fossil There are problems with the CUDA libraries in the Colab v2
thats a bot, also this is not an help channel, ask for help in #1192011222023950368 or #✨│ai-help and give more details
I'm sorry, it's just that in Colab it said to do Ping
its fine, was just telling you thats not a real person, if you give some details in the help channel i can try to help
share the colab link in an help channel
Thanks dude
Ayo? @chrome rover level 1 !!! 
do any of u guys have high quality bfdi ai voices?
i need it
Version made by BenjaminBE4
Hi, who has a model of a Russian girl?
Hello
Hello Everyone, I am Yash Jain currently learning some ML and have some experience in building web apps
How much will I have to pay someone to make me a solid voice model?
Takes me awhile and I don’t feel like doing it
usually its 25 euros/dollars
Hi all! Looking forward to exploring and learning more with AI
Ayoo, best AI to edit images?
I'm not
want a cookie?
yes it does btw
Ayo? @lethal flax level 6 !!! 
maybe ask in #🔍│help-ai-art , i think img2img in stable diffusion is what u are looking for
see, disengaging for source of numb prevents bandwidth tapping. :)
That level of bombastic response chain and tree formation will get you blocked if it continues. :)
“Ohhh no a random user I don’t care about blocked me what am I going to do oh noooooooo”
You sound like a fake ai product pyramid scheme throwing random terms to make their product look better
Yes if you set it up with the audio cable, pc only
make sure it’s a nvidia GPU (16 series or better)
1.3 seconds is not close to enough
What’s your GPU?
Intel GPU?
Not saying cpu
Which intel gpu
Ayo? @wanton ruin level 1 !!! 
what is better Harverst or Crepe?
Task manager - Performance - GPU 1
RMVPE
Hello
thx
https://github.com/deiteris/voice-changer/releases/tag/b2154 download the 001 file and the 002 file and unzip the 001 file via 7zip
New game is out!
aint noway this guy isnt some sort of AI rn
bro is acting like the most general Skyrim NPC fr
use only #1159290752195633273 , i will delete your promo here
Simply run MMVCServerSIO.exe
Make sure you run setup64
if you change tune
And make sure your downloading VAC Lite NOT VAC trial
Also make sure it’s not your default mic/speaker
After you set it up on w-okada set your output to line 1
And on Roblox set your input to line 1
Yes you can
“Input device” on the in game settings
Hoiii
Ayo? @wanton ruin level 2 !!! 
It will unzip when you unzip teh 001 file
As long as it’s the same name and in the same directory
Nobody realised that we don't have Mr. Bean voice pack
Ayo? @elder willow level 1 !!! 
wth it does even mean
yep, you're now blocked. Good luck :)
people are BORN like this, youre being dumb
Ayo? @tawdry quail level 5 !!! 
thank god
Hi
bros literally disrespecting people with down syndrome lol
where?..
hi
Hello
can i get 8 pings here for no reason at all
AI HUB Docs
