I tried this, but it said my GPU is to slow to train a voice.

Shit tier license, 2b data set, nuking of 4b in favour of a rushed product by corpos, loss of devs due to absolutely mental decisions by managment. How can SD3 be a future of AI models with it itself has no future from the get go?

You CAN run It on LIGHTING AI

i dont know why but im stuck at ckpt part..Giving me error every time..Can anyone help?

But elevenlabs has Bulgarian 🥺

f--cking waste of time

What website is this?

Thanks! Can I use these methods for audiobooks with synthetic voices?

Does it work on Ubuntu as well?

but how do i upload my chatbot to my website?

I couldn't get past 2 minutes of tutorial, there were so many errors, some I solved, others were impossible to solve. 4 hours trying. Still, thank you very much for your efforts, unfortunately I gave up trying

why is it that my TextGen web ui doesn't look like the one in the video? I'm not seeing the settings that is changed in the video...

Only seasoned animators recognize how laughable this tool it... It was explained to me , and to be honest they giving us baby food and calling it solids. I think wait for a few more months for this to become truly ground breaking, for now not much time has been saved cuz you still have to edit arcs that dont make sense with a human intervention.

ai “animators” trying their best trying not to say “ai animation is better than real animation” for one second:

How to download SXDL-STYLE.json file

I simply can't seem to make it work. I'm always ending up with some errors. Tried basically the entire day

First video I disagree with you on ...respectfully. The future of AI Models is open-source. I do agree that the fee is cheap, but the censorship is an issue, not just for nudity, but for realistic art, you need to sometimes push the envelope.

So basically... I went to the video in the first place to learn how to properly caption training images after being intimidated by the thought of precisely describing everything for a style... only to be told to suck it up. UGH.

Finally, a video on style LoRA! Very thankful for it. My VRAM isn't so good that I can train/generate stuff on SDXL, but this guide is so general that I can rely on it even for stuff based on SD1.5. I suppose the only difference would be that I'll still be stuck on 512 x 512 resolution and some other minor differences. Thank you very much!

good luck getting an answer

I don't know if it's worth it to fight with flash attention package. My 12 GB of VRAM is little to low, and when normal RAM is used things go slow.

The Anatomy is really bad!

I got this error when I want to start the webui: ModuleNotFoundError: No module named 'requests'

"No effort required whatsoever..." That pretty much sums it all up.

Need Windows and VS... No thank you, I'm out.

There are thousands of images of people lying down on the internet. It's crazy to me how they wouldn't include that in their dataset since it's going to be a fairly common thing people will try to get SD to generate. Dall-E 3 does it quite well.

SD3 is hot garbage.

LMAO

TTS option is not showing to me :o

The real issue is not the model itself, but the license offered by SAI. The doubt it has created in the community doesn't encourage anyone to train LORA or checkpoints. Until SAI clarifies its position, no one will want to waste computation time on SD3, at the same level as SDXL. As a result, while we could already be seeing improvements through the community, SAI has cut itself off from one of its assets: the users who advance its product.

Hello @aitrepreneur, I got this error when launching the webui "OSError: [WinError 126] The specified module could not be found. Error loading "D:\*****\Softwares\xtts-webui-v1_0-portable\webui\venv\Lib\site-packages\torch\lib\torch_python.dll" or one of its dependencies." Can you please help! Not a bright guy here :/

Holy king of yapping

Too censored

0:25 Nooo! It's not from scratch. You do know that this AI stuff uses a MODEL right? A MODEL that is created BASED ON A LOT OF DATA. I'm so frustrated when people don't understand how things work.

Unless it can run on a potato without turning it into charcoal then nope... ElevenLabs is still king of TTS.

I don't get the people that says comfyui is hard to understand. Everything in A1111 is hard to understand because you don't build it, the tabs are already there.

"Python was not found"

bro that fitness pacer audio game me flash backs

I was wondering what is ozio, but in the end realized guy can't pronounce word audio properly. This is audio-to-audio, not ozio-to-ozio 🤣

What should the regularization images contain for style training?

Missed the pip install -r requirements.txt the first time I tried to installed. Completely deleted it and tried it again and saw it in the video. Glad I learned that I needed +cpu as my gpu doesn't support cuda which is the cu118. After installing it again, it's finally working :D

Is there any way you can make this work on an AMD GPU? I have a RX 6900 XT and I would love to try it

If you do a tutorial but you don't give us what we need it's useless. lol

the people complaining feels like a botswarm tbh

I am so lost. I think its better if you made a clean install video with steps.

Getting Error while importing the reference wave file is there any solution for it ?

This extension doesn’t pop up in the tabs at the top when I installed, any help ?

If you have any troubles, and you have it, just install Microsoft C++

@Aitrepreneur when do you think/expect we'll have a suno / udio musical local models? Thanks ❤

ModuleNotFoundError: No module named 'safetensors' What should i do?