if i add again the lora directory into extra networks tab i think it will default to that lora again
if i add again the lora directory into extra networks tab i think it will default to that lora again and will add it to all my prompts
Fcould be automatic1111 bug
Fthey broken some things
Fi am working with this and latest version not working
F
Amaybe, today i deleted my old sd and installed it on my new drive so could be something from my installation...
CHey Furkan! This is the content of the next video ?
Fyes. actually i found even a better way
Fbut taking huge time tests
Cyou are amazing haha
Fchosen this as a beginning
F
Fthis is original
F
For should i pick another beginning i dont know do you think looking cool enough
F
F
Zhow can i use a sanity prompt to gauge my training?
Fi use photo of ohwx by tomer hanuka
Fawesome found an AI based free open source deflicker as well
ZHow can I donate to your work?
Zand what am i looking for when i do the sanity prompt? i tried cartoon drawing of ohwx woman but not really even sure what i'm looking for
Fyou can support us with patreon or crypto
FZwhich crypto do you prefer?
Fi got binance account any works.
Fwith sanity prompt you are looking for model can stylze your image or not
Zso the sanity prompt will eventually become your image?
Zive used "drawing of charactername" for mine but idk much about this
Fyes it will lose style
Fthis can also work of course
Zso do i want to stop the training right before it switches over, or before it switches over, or right after
Fbest way is compare checkpoints
Fstop after switches over
Zand i'm assuming the more epochs I do, the more versatile my model will be?
Fit will be lesser flexiable
Zso i want to do as few epochs as possible while still getting my character?
Zi'll run some test, and i'll do that tomer hanuka image
ZZi'll train for a while, and the images will look perfect, then like 10 or 20 epochs later, their faces just get all blurry, is it overtrained at that point?
Ayes, the more you train, the higher the chances to overcook your model
Zi'm assuming that's based on the scheduler as well
G@Furkan Gözükara SECourses Hello, I am new here, and I am trying out training a model for the first time on Google Colab. I have been following this video:
https://www.youtube.com/watch?v=mnCY8uM7E50
To preface, I am not a programmer, just a hobbyist interested in generating AI art of my original character (fictional). So sorry if I ask any dumb questions!
I am trying to start the training. I click the arrow to run the cell starting with
and a message appeared saying:
Is that normal? Did I do something wrong? Can anyone help? I'd appreciate it. Thank you!
https://www.youtube.com/watch?v=mnCY8uM7E50
To preface, I am not a programmer, just a hobbyist interested in generating AI art of my original character (fictional). So sorry if I ask any dumb questions!
I am trying to start the training. I click the arrow to run the cell starting with
!accelerate launch train_dreambooth.py \
and a message appeared saying:
[15:34:11] WARNING The following values were not passed to
Is that normal? Did I do something wrong? Can anyone help? I'd appreciate it. Thank you!
YouTubeSECourses - Software Engineering Courses
Our Discord : https://discord.gg/HbqgGaZVmr. How to do free Stable Diffusion DreamBooth training on Google Colab for free. If I have been of assistance to you and you would like to show your support for my work, please consider becoming a patron on 
https://www.patreon.com/SECourses
Playlist of Stable Diffusion Tutorials, Automatic1111 and Goo...
https://www.patreon.com/SECoursesPlaylist of Stable Diffusion Tutorials, Automatic1111 and Goo...
Cdo you have the little video ?
C@Furkan Gözükara SECourses
Fi'm trying loras but i'm gettiing this kind of look
F
Fis that overtraining?
For still need more training? face doesn't even look much like subject
Nwhy cant i get a perfect spider man kit on my self 
Fdoes your model knows about spiderman?
