it says yours corrupted
it says yours corrupted
Fi would make a fresh install and download sd 1.5 again
Fi have links in description
Gah ok, I'll try that now!
Fcould be that google colab provided gpu weaker
Fi tryed with 1 sample as you sugest me and worked, but with more than this I got that error. But days ago it was working with 10 samples, that's what I dont understand
Ftried 2 3 4 5 1 by 1?
Fmaybe google colab provided gpu is different this time
FAh, ok!
FAnyway, thanks for the help!
Fyou are welcome
HGM @Dr. Furkan Gözükara … I noticed a Runpod user was able to use the kohya gui using a Linux installation.
Does this mean we should be able to run any Linux based repos in a pod?
Does this mean we should be able to run any Linux based repos in a pod?
HGitHub
(WIP) A port of bmaltais/kohya_ss for Linux. Contribute to Thund3rPat/kohya_ss-linux development by creating an account on GitHub.
GHey! So I've downloaded and replaced but still getting these issues
Geverything if that helps, the first generation was a neat text-image, no ControlNet
BHi , can i use ControlNet in stable diffusion colab ?, i tried but it keep error all the time when i generate image
H@IVG did you try to get controlnet on runpod yet?
Isorry no - I haven't...
MHey all, trying out ControlNet from the repo, with the prompt
photo of an owl. DDIM 30 steps. control_sd15_scribble.pth Anybody know what might be going wrong here?
M
SHey there, sorry for bothering,
I already have Automatic1111 with 1.5 since a long time and it s working perfectly, But, I followed your tutorial to install ControlNet step by step, but still couldn't make it to work (I didn't have that ControlNet Bar/Triangle in the UI)
I would be very thankful if someone could guide me to know the issue
Thank you in advance !
I already have Automatic1111 with 1.5 since a long time and it s working perfectly, But, I followed your tutorial to install ControlNet step by step, but still couldn't make it to work (I didn't have that ControlNet Bar/Triangle in the UI)
I would be very thankful if someone could guide me to know the issue
Thank you in advance !
YThanks for the tutorial on last video i got this result
Y
KDamn this is nice
Gyeah looks great!
SWow, which SD model is this?
Yim using 1.5, the one that come with the automatic1111, i use prompts, helmet, bioshock
SThank you, incredible result
Yyeah really impressive, i noticed the sketch has to be clear
Yotherwhise u get weird results lol
Y
MA new Flutter project.
M(but I'm not sure if it's working as expected yet, see the owl 
)
)AHello, Hello, Quick question does anyone know is there a Formula for Embedding Learning Rate and Batch Size for best results
AI am trying to train Textual Inversion on my RTXA5000 card for Stable diffusion 2.1 and not getting quite good results.
Cyou are improving
Yhow are u guys getting good results? every model i download looks, kinda ok ;/ i think it's my prompts, idk.
Frunpod io runs on a linux os
Fhello. could you install directly in C drive? still looks to me as path permission error
Fsure i can help. but need more info
Fvery good congrats
Fthank you. any more suggestions?
FI would first test 1 batch size 1 gradient and default learning rate
Fyou tried that?
Fthe batch size and gradient actually changes how model learns . it is mini batches vs full batches. which one better is debated
AYeah, Tried with 2 Vectors but seems very inflexible
Av5 for 20 input images working slyly better but not quite there yet
Fye it requires experimenting
AI'll try more combinations and see what it comes up with.
GHi! I think somehow the models didn't download properly, they were only just over 1gb when I did a git pull, but 5gb when I downloaded each individually