Software Engineering Courses (SECourses)•3y ago

ok i see. so probably not for me, since i am no coder

DDeadMan1999 miniGPT also needs 12GB VRAM minimum, that is a disadvantage as well.

rafrafOP•4/27/23, 12:39 PM

i have a 4090

Rrafraf ok i see. so probably not for me, since i am no coder

Furkan Gözükara SECourses•4/27/23, 12:46 PM

yep you probably need someone else to do coding

FFurkan Gözükara SECourses yep you probably need someone else to do coding

rafrafOP•4/27/23, 12:47 PM

i suppose miniGPT would be a workaround the coding that i lack. It could write the python for my simple description of what needs to be done to the txt files. But i suppose even that would be a challenge

DeadMan1999•4/27/23, 12:49 PM

ill try to get miniGPT running on my 3060, if it works then i could help you further

DeadMan1999•4/27/23, 12:50 PM

i am out of town for a couple of days though, will be back on 3rd May

DDeadMan1999 ill try to get miniGPT running on my 3060, if it works then i could help you fur...

rafrafOP•4/27/23, 12:50 PM

Ok, that could be an interesting project to work on

Rrafraf i suppose miniGPT would be a workaround the coding that i lack. It could write t...

Furkan Gözükara SECourses•4/27/23, 12:54 PM

i doubt that miniGPT will produce captions as you are looking for

Furkan Gözükara SECourses•4/27/23, 12:54 PM

but you can try

Furkan Gözükara SECourses•4/27/23, 12:54 PM

i plan to make a tutorial for miniGPT as well

Furkan Gözükara SECourses•4/27/23, 12:54 PM

currently post processing kohya lora tutorial

Furkan Gözükara SECourses•4/27/23, 12:55 PM

as the number of training images increase it takes really a lot time to train :d

FFurkan Gözükara SECourses i doubt that miniGPT will produce captions as you are looking for

rafrafOP•4/27/23, 1:01 PM

Maybe you are right, and this might be too personal and specific for an ai agent to figure. But i guess, with a bit of explaining, with some template language instruction, it might get used to it. Like for instance describe the type of clothing and material and accessories... We will see. If it works, it would cut off 70% of the work in trainging

FFurkan Gözükara SECourses currently post processing kohya lora tutorial

rafrafOP•4/27/23, 1:01 PM

that would be great

FFurkan Gözükara SECourses currently post processing kohya lora tutorial

rafrafOP•4/27/23, 2:33 PM

I look forward to it!

DDeadMan1999 ctrl+f > find in files > "input directory where files are present", in Filters p...

rafrafOP•4/27/23, 2:42 PM

worked perfectly. thanks man

FFurkan Gözükara SECourses Not much else you can do

Khang•4/27/23, 3:17 PM

I just found out about two weird bugs in SD on Runpod:

The first one is that LOAD SETTING tooks forever, but if I click the Saving tab and then click Load Setting, everything loads fine.
The second one happens when I click on the Advanced tab, located at the end of the Setting tab of Dreambooth, I cannot click on anything else and must reload the UI
Well at least now I can load the setting.

Khang•4/27/23, 3:22 PM

Hi guys, in Dreambooth, I set the 'Class Images Per Instance Image' to 50 and added 1500 images to the 'Classification Dataset Directory.' I checked the folder path and it is correct. However, SD is still attempting to generate 1500 images. Should I set 'Class Images Per Instance Image' to 0?
Thank you very much.

KKhang Hi guys, in Dreambooth, I set the 'Class Images Per Instance Image' to 50 and ad...

Furkan Gözükara SECourses•4/27/23, 4:14 PM

show me screenshot of path please

Daniel•4/27/23, 4:14 PM

Hi, i have question about SD Dreambooth: have they fixed the problems with it? i've read about it getting broken after some updated and not producing good results. on my first attempts with it (using lora)i didnt have great results, following you instructions. although my data set only had me in different angle and not distances and cloths. wanted to know if the tool is the problem or i just need to try more stuff.

DDaniel Hi, i have question about SD Dreambooth: have they fixed the problems with it? i...

Furkan Gözükara SECourses•4/27/23, 4:14 PM

currently it is working very well

Furkan Gözükara SECourses•4/27/23, 4:14 PM

they fixed bugs

Daniel•4/27/23, 4:17 PM

okay nice, and i have a 3060 ti with 8gb vram. do i need to use lora or i can run it without it?

DDaniel okay nice, and i have a 3060 ti with 8gb vram. do i need to use lora or i can ru...

Furkan Gözükara SECourses•4/27/23, 4:18 PM

you need lora

Furkan Gözükara SECourses•4/27/23, 4:18 PM

you cant do dreambooth

Furkan Gözükara SECourses•4/27/23, 4:18 PM

actually right now i am post processing kohya lora tutorial

FFurkan Gözükara SECourses actually right now i am post processing kohya lora tutorial

Daniel•4/27/23, 4:19 PM

i will catch that

Daniel•4/27/23, 4:19 PM

thank you

xariis_f•4/27/23, 5:05 PM

Hi everyone, I hope you're all doing great. I followed this tutorial https://youtu.be/dYt9xJ7dnpU to install Kandinsky 2.1 and generate AI art using my graphics card. I followed every step and it was going well until I ran this code to download the files and models:
model = get_kandinsky2(
'cuda',
task_type='text2img',
cache_dir='/tmp/kandinsky2',
model_version='2.1',
use_flash_attention=False
)
I tried deleting and re-downloading the files, but the same error keeps appearing every time. If anyone has any ideas on how I can fix this, it would be greatly appreciated. Thank you.

YouTubeSECourses

Midjourney Level NEW Open Source Kandinsky 2.1 Beats Stable Diffusi...

Discord : https://bit.ly/SECoursesDiscord. Kandinsky 2.1 is truly exceptional, and it is on par with Midjourney. In this video, I will compare Kandinsky to Stable Diffusion and provide a comprehensive tutorial on installation and usage. If I have been of assistance to you and you would like to show your support for my work, please consider becom...

xariis_f•4/27/23, 5:06 PM

Hiccup•4/27/23, 5:34 PM

Is your python path set correctly xD

Crazotor•4/27/23, 6:21 PM

hi guys, I have just started to learn SD for a week now. I am trying to train with dreambooth but I just cant get it to work like I want to. I have seen SEcourses video's for the best settings and tried those but I am a little confused which ones to use. I have a RTX a4000 card with 16GB of vram. Should i use EMA and 8bit adam or lion, which mixed precision and somehow i cant use xformers (I can only use the default option). Can you guys help me?