can i do that without nuking windows?
can i do that without nuking windows?
Gi dont mind doing it, either way
Gitll take 1 hr
Fi dont know 
if all works without error it should work
if all works without error it should work Fbut reinstall best way
Gok ill try, it it doesnt work ill do fresh windows
Gok brb in a few hrs lol
Fsure
Djust uninstall python and delete all leftovere folders
Finitial install really matters
Ffollowing this really important
FYouTubeSECourses
Welcome to the Pillars of AI Application Libraries: How to Install Tutorial! 
Are you ready to embark on a journey of installing AI libraries and applications with ease? 
In this video, we'll guide you through the process of installing Python, Git, Visual Studio C++ Compile tools, and FFmpeg on your Windows 10 machine. 
We'll also show you ho...
Are you ready to embark on a journey of installing AI libraries and applications with ease? In this video, we'll guide you through the process of installing Python, Git, Visual Studio C++ Compile tools, and FFmpeg on your Windows 10 machine. We'll also show you ho...Finstall into c:/python310
Fc++ tools
Fcuda
FI still have the problem despite the sub-folder. Is it possible that the jpg format is causing the problem? Usually it's the png format that's not taken into account. Also, I haven't created a caption file. Is it possible that this is blocking the training?
FI renamed the folder
Fin train_data_dir
Fstill wrong :d
Fit has to start with repeating_
Fso like
F1_angry
Fbut it would be still wrong
Fit can be like
F1_angry ohwx man
Guse dataset prep
Fadding a new prompt to testing
Gim usuing 3.10.9 is that why bro?
Gpython
FI have to rename all the images?
�Do the images have to be renamed in numerical order too or that doesn't matter? I tend to always have them 0, 1, 2 , 3, etc.
Fno it doesnt read image names
Fit reads folder names
Funless caption exists
Fflux images are so clean
Fi cant wait to fine tune
F
DWith sdxl you can replicate the same behavior is you caption properly your dataset "name man, prescription glasses" then in the inference if you don't prompt for the glasses it removes it even if all the images are with glasses, I test it and it works perfectly
Fwith sdxl captions really reduces likeliness but perhaps only eyeglasses can be added
Dreduces likeness if you use descriptive tokens, but adding accessories like glasses or clothing is not a problem
Gbruhhh
Gi do step2 batch and it breaks
Ji asked chat GTP how to, it worked very well for me, no need for new windows install 
Gi updated to 3.10.11 python too
Fdont use that
Fuse my starter and see
Fand any error at step 2?
M@Dr. Furkan Gözükara what is this
Its justa mazing!!
Its justa mazing!!
Sdr Furkan when do you think could be a kohya flux tutorial update_? i saw and i did SDXL but seem to diferretn form flux process
Dto avoid the problem I use captions with comma "ohwx man, prescription glasses" on that way it separate the concepts