looks like you didnt download or give model paths accurately
looks like you didnt download or give model paths accurately
FLR changes only when you change batch size
PWhere to give model paths,I just downloaded models by the commands in the txt file and all the modesl are present in downloads folder
PAnd one more error koya isn't showing flux dev option after loading config
Fthat means you didnt do accurately
Fas i guessed
POk then should i delete this gpu and start everything fresh?
Fno you should download models accurately
Fand give their accurate path
Falso did you run kohya installer on massed compute?
Fyou dont use already isntalled one
Ffollow Massed_Compute_Kohya_FLUX_Instructions.txt
PYes I Run from there in the folder from terminal not from desktop
Fdid you copy pasted into downloads folder?
Fare you on massed compute or runpod?
PMassedcompute
Fok then i recommend close all cmds
Fand do from beginning
Fit takes like 2 min to install
Fperhaps set a fresh config
POk fine will watch your tutorial with full attention and follow everything
PAgain
FYouTubeSECourses
If you want to train FLUX with maximum possible quality, this is the tutorial looking for. In this comprehensive tutorial, you will learn how to install Kohya GUI and use it to fully Fine-Tune / DreamBooth FLUX model. After that how to use SwarmUI to compare generated checkpoints / models and find the very best one to generate most amazing image...
F1:13:49 Massed Compute (cheap private cloud training) part of the tutorial starts with how to install Kohya GUI for FLUX training
Fif machine is not broken you skipped a part 100%
PYes this one only tutorial
Fi am running 6 different trainings on massed compute image 
F
Ftoday started
Fexactly same way
PMight be skipped some small step got busy in some other task
N@Furkan Gözükara SECourses hey dr are you trying sigma vision on your training as well to figure out best settings and more?
Tit's trying to load a model from non existing path
you can actually guess which one by the order of loading: vae -> clip -> t5 -> flux
you can actually guess which one by the order of loading: vae -> clip -> t5 -> flux
TJust read news than 5000 Nvidia RTX series dropped support for a considerable list of PC games utilising 32-bit PhysX.
Games unsupported by 5000 RTX series include Batman: Arkham Asylum, Mirror's Edge, Metro 2033, Mafia II, Batman: Arkham City, Borderlands 2, Metro: Last Light, Batman: Arkham Origins, Assassin's Creed IV: Black Flag
Games unsupported by 5000 RTX series include Batman: Arkham Asylum, Mirror's Edge, Metro 2033, Mafia II, Batman: Arkham City, Borderlands 2, Metro: Last Light, Batman: Arkham Origins, Assassin's Creed IV: Black Flag
T:nevozmozhno:
DWhat's up with 5xxx series? It seems they've been in the negative news alot lately. Was 4xxx series received much better or does this happen everytime?
DI'm honestly thinking of strapping multiple 4060ti together. Is anyone here running such a multi-GPU setup?
T4000 series was received not super good but with much less criticism
I guess people are expecting much more premium experience with GPU prices increasing, not realising that price increase is not due better quality product but due to shortage and monopolisation
I guess people are expecting much more premium experience with GPU prices increasing, not realising that price increase is not due better quality product but due to shortage and monopolisation
Fcan you give me link
F5000 not supporting everyuthing yet
Fwe are waiting pytorch
Fi trained this
Fit works
Fyou can use our config
Fi, was gonna publish an article but the cloud machine hdd died
Fso all data lost
Noh haven't checked patreon yet, great!
better results than previous flux model trainings?
better results than previous flux model trainings?
Ncould you share the post? can't find it on patreon
Fsure here
FPatreon
Get more from SECourses: FLUX, Tutorials, Guides, Resources, Training, Scripts on Patreon
Nwait these were the previous model trainings
