Software Engineering Courses (SECourses)•3y ago

Hi all, i have been using runpod for A1111, since im using 4090 i want to fully maximize the gpu to

Hi all, i have been using runpod for A1111, since im using 4090 i want to fully maximize the gpu to generate image. can i know if i can divide the GPU process so that two people can generate the image at the same time without having to queue up with each other?

minxxOP•10/26/23, 3:36 AM

or perhaps just need to tweak the command line args in webui-user.sh?

Mminxx Hi all, i have been using runpod for A1111, since im using 4090 i want to fully...

Furkan Gözükara SECourses•10/26/23, 12:09 PM

start 2 instance of auto1111.

FFurkan Gözükara SECourses We have 16gb config

mrLLUU•10/26/23, 12:15 PM

had not found that yet, thanks

MmrLLUU had not found that yet, thanks 🙂

Furkan Gözükara SECourses•10/26/23, 12:22 PM

here https://www.patreon.com/posts/very-best-for-of-89213064

_Captain_•10/26/23, 2:17 PM

@Furkan Gözükara SECourses debugged the text encoder bug myself and reproduced the answer from arazela.
If you are curious too, here the debug output.

_Captain_•10/26/23, 2:18 PM

after implementing the fix from koyha (only local because it's not pushed yet):

_Captain_•10/26/23, 2:19 PM

the array is fixed

_Captain_•10/26/23, 2:20 PM

will test it to see if it makes a difference

__Captain_<@205854764540362752> debugged the text encoder bug myself and reproduced the an...

Furkan Gözükara SECourses•10/26/23, 2:24 PM

awesome

_Captain_•10/26/23, 3:49 PM

@Furkan Gözükara SECourses Wohooo! Big difference

can't share result because of private dataset, but man, looking forward to your next comparision

I think it will have more impact on things the text encoder doesn't already know.

_Captain_•10/26/23, 3:51 PM

used sdxl_train.py with .caption (full text descriptions) and .txt (with tags), no reg images

_Captain_•10/26/23, 3:53 PM

one line of code might improve sdxl a lot

crazy stuff.. always the same with coding xD

__Captain_<@205854764540362752> Wohooo! Big difference 😱 can't share result because of p...

Furkan Gözükara SECourses•10/26/23, 4:00 PM

awesome

GeorgeClintonGeorgeBush•10/26/23, 11:22 PM

What's the best way to fix weird eyes/pupils on your images?

GGeorgeClintonGeorgeBush What's the best way to fix weird eyes/pupils on your images?

Furkan Gözükara SECourses•10/26/23, 11:44 PM

inpainting

Furkan Gözükara SECourses•10/26/23, 11:44 PM

but first improve your training dataset

FFurkan Gözükara SECourses inpainting

GeorgeClintonGeorgeBush•10/26/23, 11:45 PM

Thanks. ADetailer right?

GGeorgeClintonGeorgeBush Thanks. ADetailer right?

Furkan Gözükara SECourses•10/26/23, 11:45 PM

yep

FFurkan Gözükara SECourses but first improve your training dataset

GeorgeClintonGeorgeBush•10/26/23, 11:47 PM

Do you know what kind of bad images causes weird eyes in your model? I don't know how to improve my dataset further

GGeorgeClintonGeorgeBush Do you know what kind of bad images causes weird eyes in your model? I don't kno...

Furkan Gözükara SECourses•10/26/23, 11:49 PM

image quality focus lightning distance

Furkan Gözükara SECourses•10/29/23, 9:37 PM

@helen i am checking your issue right now

Furkan Gözükara SECourses•10/29/23, 9:57 PM

@helen here images they are working. there must be some step you skip. did you make container size 20 gb before install?

Furkan Gözükara SECourses•10/29/23, 9:57 PM

Furkan Gözükara SECourses•10/29/23, 9:57 PM

Furkan Gözükara SECourses•10/29/23, 9:57 PM

i tested both templates

FFurkan Gözükara SECourses <@1161756280994676806> here images they are working. there must be some step you...

helen•10/29/23, 9:59 PM

OK, I'll try again and check container size

thank you

Hhelen OK, I'll try again and check container size😊 thank you

Furkan Gözükara SECourses•10/29/23, 10:01 PM

you are welcome.

Furkan Gözükara SECourses•10/29/23, 10:01 PM

also pick rtx 3090

David Ce•10/30/23, 2:22 AM

Hey @Furkan Gözükara SECourses
Please I've been having this issue and don't know how to fix it
Could you help?

David Ce•10/30/23, 2:28 AM

The error has changed after editing the webui_user.bat file to this

DDavid Ce Hey <@205854764540362752> Please I've been having this issue and don't know how...

Furkan Gözükara SECourses•10/30/23, 3:18 AM

just replied you in qwen-flux-wan-such

felixsanz•10/30/23, 7:51 PM

i can't make use of roop/insightface/whatever in runpod, does anyone know why? it's banned or something? CUDA execution provider doesn't appear

Ffelixsanz i can't make use of roop/insightface/whatever in runpod, does anyone know why? i...

Furkan Gözükara SECourses•10/30/23, 9:44 PM

try auto installer working i tested yesterday : https://www.patreon.com/posts/auto-installer-84511510

Patreon

Auto Installer Script For Roop (DeepFake) On RunPod & Example Image...

Get more from SECourses: Tutorials, Guides, Resources, Training, MidJourney, Voice Clone, TTS, ChatGPT, GPT, LLM, Scripts by Furkan Gözükara on Patreon

felixsanz•10/30/23, 9:47 PM

i'm not using roop. i created my own app using insightface

felixsanz•10/30/23, 9:47 PM

but mine uses more or less the same stuff

felixsanz•10/30/23, 9:48 PM

it's just that i can't get the cuda execution provider here, dunno why

Furkan Gözükara SECourses•10/30/23, 9:48 PM

i see dont know

felixsanz•10/30/23, 10:16 PM

well, good to know it should work xD

Furkan Gözükara SECourses•10/31/23, 2:40 PM

trying to fine tune

Furkan Gözükara SECourses•10/31/23, 2:40 PM

https://github.com/coqui-ai/TTS/issues/3125

GitHub

Need help with ljspeech\xtts_v1\train_gpt_xtts.py - Fine tuning a s...

I am trying to make training work on first official raw dataset of LJSpeech-1.1 My aim is fine tuning a single voice to get eleven labs level quality Then hopefully I will release this as a tutoria...

Latest iPhone•10/31/23, 6:09 PM

Here's a fun little commandline client I made for ChatGPT:

minigpt.rb2.02KB

Only•11/1/23, 12:58 AM

hii,anyone knows why ozen its transcribing my uploaded voice for training in different language instead of the speaking language as how the whisper is doing it

Only•11/1/23, 12:59 AM

i have edited ozen.py and modified the default model to medium and also changed from cuda to cpu as i dont have a gpu at the moment.Thanks!

Only•11/1/23, 1:16 AM

Lightning automatically upgraded your loaded checkpoint from v1.5.4 to v2.1.0. To apply the upgrade to your files permanently, run

python -m pytorch_lightning.utilities.upgrade_checkpoint C:\Users\Hp\.cache\torch\pyannote\models--pyannote--segmentation\snapshots\2ffce0501d0aecad81b43a06d538186e292d0070\pytorch_model.bin

python -m pytorch_lightning.utilities.upgrade_checkpoint C:\Users\Hp\.cache\torch\pyannote\models--pyannote--segmentation\snapshots\2ffce0501d0aecad81b43a06d538186e292d0070\pytorch_model.bin

Model was trained with pyannote.audio 0.0.1, yours is 3.0.1. Bad things might happen unless you revert pyannote.audio to 0.x.

Only•11/1/23, 1:16 AM

could be because of pyannote?

OOnly Lightning automatically upgraded your loaded checkpoint from v1.5.4 to v2.1.0. T...

Furkan Gözükara SECourses•11/1/23, 11:30 AM

i dont know this

OOnly hii,anyone knows why ozen its transcribing my uploaded voice for training in dif...

Furkan Gözükara SECourses•11/1/23, 11:30 AM

you can edit files to change language

Furkan Gözükara SECourses•11/1/23, 11:30 AM

accurate

FFurkan Gözükara SECourses you can edit files to change language

Only•11/1/23, 1:42 PM

hmm,i will try to find out,as i said i set the model to medium so its ok with multilingual audios...i thinked maybe the training is done in english somehow and thats why the audio was transcribed in english, what about the traing proccess its working only if i have gpu right?as i tryed to start the training and i receive error that i there is no gpu

Jehovah•11/1/23, 2:47 PM

Hello.

Startup problem - Auto Windows Installer For SDXL Background Replacement for Product Images

A matching Triton is not available, some optimizations will not be enabled.
Error caught was: No module named 'triton'
Initializing captioner...
Initializing upscaler...
Initializing segmenter...
Initializing depth estimator...
Initializing depth ControlNet...
Initializing autoencoder...
Initializing SDXL pipeline...
Loading pipeline components...: 100%|████████████████████████████████████████████████████| 7/7 [00:08<00:00, 1.26s/it]
Traceback (most recent call last):
File "D:\pimages\background-replacement\app.py", line 150, in <module>
num_inference_steps = gr.Slider(precision=0,minimum=1, maximum=300,value=30, default=30,step=1, label="Num Inference Steps")
File "D:\pimages\background-replacement\venv\lib\site-packages\gradio\component_meta.py", line 146, in wrapper
return fn(self, **kwargs)
TypeError: Slider.init() got an unexpected keyword argument 'precision'
To continue, press any key. . .

help me solve the problem
Thank you

Hi all, i have been using runpod for A1111, since im using 4090 i want to fully maximize the gpu to

Similar Threads