Software Engineering Courses (SECourses)•3y ago

I saw this post on civitai https://civitai.com/articles/3378/which-style-training-model-looking-best

I saw this post on civitai https://civitai.com/articles/3378/which-style-training-model-looking-best-do-you-think

It's done with the same method?

JJozsef I saw this post on civitai https://civitai.com/articles/3378/which-style-trainin...

Furkan Gözükara SECourses•12/21/23, 4:58 PM

i also tried captions in that one

Furkan Gözükara SECourses•12/21/23, 4:59 PM

so that was the difference

Furkan Gözükara SECourses•12/21/23, 4:59 PM

moreover now i am using Patreon SDXL DreamBooth config

FFurkan Gözükara SECourses moreover now i am using Patreon SDXL DreamBooth config

JozsefOP•12/21/23, 4:59 PM

I'll check that out, thank you!

JJozsef I'll check that out, thank you!

Furkan Gözükara SECourses•12/21/23, 5:00 PM

you can use our SOTA captioners on Patreon

Furkan Gözükara SECourses•12/21/23, 5:00 PM

I used them

JozsefOP•12/21/23, 5:00 PM

I'll check it out, but I wrote captions by hand for all 150 images

JozsefOP•12/21/23, 5:00 PM

How many you suggest to use for style?

JozsefOP•12/21/23, 5:00 PM

Images that is

JJozsef Images that is

Furkan Gözükara SECourses•12/21/23, 5:01 PM

use as many as possible

Furkan Gözükara SECourses•12/21/23, 5:01 PM

but make sure that

Furkan Gözükara SECourses•12/21/23, 5:01 PM

it doesnt contain repeating subjects

FFurkan Gözükara SECourses it doesnt contain repeating subjects

JozsefOP•12/21/23, 5:01 PM

Will do, all of them are professional photos from a photographer.

JozsefOP•12/21/23, 5:01 PM

So quality won't be an issue

JJozsef Will do, all of them are professional photos from a photographer.

Furkan Gözükara SECourses•12/21/23, 5:05 PM

great

FFurkan Gözükara SECourses hello record video and dm me

eyepatch_2022•12/21/23, 5:42 PM

Sent, pls let me know.

Eeyepatch_2022 Sent, pls let me know.

Furkan Gözükara SECourses•12/21/23, 5:52 PM

replied

Metaphysix•12/21/23, 6:03 PM

Hi, I'm trying to do sdxl dreambooth with the patreon kaggle notebook and i get 'out of memory' error after the 4th iteration. Any idea?

MMetaphysix Hi, I'm trying to do sdxl dreambooth with the patreon kaggle notebook and i get ...

Furkan Gözükara SECourses•12/21/23, 6:09 PM

4 th iteration?

FFurkan Gözükara SECourses replied

eyepatch_2022•12/21/23, 6:09 PM

I have to commented on it

Furkan Gözükara SECourses•12/21/23, 6:09 PM

you mean steps?

Metaphysix•12/21/23, 6:13 PM

Yes

MMetaphysix Yes

Furkan Gözükara SECourses•12/21/23, 6:17 PM

Which base model you trying

Metaphysix•12/21/23, 6:31 PM

RealVis

MMetaphysix RealVis

Furkan Gözükara SECourses•12/21/23, 7:17 PM

downloaded from civitai?

Furkan Gözükara SECourses•12/21/23, 7:17 PM

what is your resolution 1024x1024?

Metaphysix•12/21/23, 7:18 PM

yes 1024,1024 and the training images are 1280x1536
now it works with the

stabilityai/stable-diffusion-xl-base-1.0

stabilityai/stable-diffusion-xl-base-1.0

MMetaphysix yes 1024,1024 and the training images are 1280x1536 now it works with the `stabi...

Furkan Gözükara SECourses•12/21/23, 7:22 PM

1280x1536 will use more vram

Furkan Gözükara SECourses•12/21/23, 7:23 PM

resize them to 1024x1024 yourself before start training

Furkan Gözükara SECourses•12/21/23, 7:23 PM

because it will downscale only 1 side to 1024

virginia•12/21/23, 7:27 PM

Furkan, do you offer new checkpoint settings? and do you mean if i train checkpoint, but can finally extract lora from it, too?

Vvirginia Furkan, do you offer new checkpoint settings? and do you mean if i train checkpo...

Furkan Gözükara SECourses•12/21/23, 7:43 PM

new checkpoint settings are shared on patreon

Furkan Gözükara SECourses•12/21/23, 7:44 PM

and you can extract lora from them

Furkan Gözükara SECourses•12/21/23, 7:44 PM

working nice

B0nd•12/21/23, 7:45 PM

Do regularisation images work better when training on dreambooth when they have caption files with them?

BB0nd Do regularisation images work better when training on dreambooth when they have ...

Furkan Gözükara SECourses•12/21/23, 7:54 PM

i never tried them with caption

Mnova•12/21/23, 8:13 PM

someone i know tried your dreambooth notebook and got this error. do you know what could be wrong?

MMnova someone i know tried your dreambooth notebook and got this error. do you know wh...

Furkan Gözükara SECourses•12/21/23, 8:13 PM

you forgatten to enable gpu

samopopo•12/21/23, 9:34 PM

Furkan where you going for vacation?

samopopo•12/21/23, 9:34 PM

Can I come with you Haha

Ssamopopo Furkan where you going for vacation?

Furkan Gözükara SECourses•12/21/23, 9:39 PM

i dont have any vacation haha

not even weekends

Furkan Gözükara SECourses•12/21/23, 9:39 PM

checkout the newest article : https://medium.com/@furkangozukara/comparison-between-sdxl-full-dreambooth-training-vs-lora-training-vs-lora-extraction-44ada854f1b9

Medium

Comparison Between SDXL Full DreamBooth Training vs LoRA Training v...

Hello everyone. I have trained myself recently by using Kohya GUI latest version. Used official SDXL 1.0 base version.

Deleted User•12/21/23, 9:41 PM

he's always working working working

shortdwarf•12/21/23, 10:27 PM

Anyone know why I always get bad results from Adetailer? Does it only work well on small further faces? On my images where my face is pretty large (think portrait) Adetailer always makes my face look worse, like its set to a higher CFG Scale (its not) I followed the same settings @Dr. Furkan Gözükara used in the SDXL Dreambooth training video. For some reason this has always been my results with Adetailer and I'm not sure what I could be doing wrong

Sshortdwarf Anyone know why I always get bad results from Adetailer? Does it only work well ...

Furkan Gözükara SECourses•12/21/23, 10:48 PM

can you show previous after and your settings?

Furkan Gözükara SECourses•12/21/23, 10:49 PM

i am using adetaler all the time

FFurkan Gözükara SECourses i dont have any vacation haha 😄 not even weekends

JozsefOP•12/21/23, 10:49 PM

You are in that same position?

JozsefOP•12/21/23, 10:49 PM

AI is hard work, thank you for all these tutorials, I would need 48 hours a day to get everything done.

JozsefOP•12/21/23, 10:50 PM

BTW, do you think teaching SDXL style on a realvisXL model would be better? It seems the custom SDXL models are still flexible with prompts more than the 1.5 were.

JJozsef You are in that same position? 😄

Furkan Gözükara SECourses•12/21/23, 10:54 PM

yes D

I saw this post on civitai https://civitai.com/articles/3378/which-style-training-model-looking-best

Similar Threads