just the kohya dataset prep is a bit weird to understand in their UI
just the kohya dataset prep is a bit weird to understand in their UI
Factually it is easy once you understand logic
Fi explained in this video in details
FYouTubeSECourses
Ultimate Kohya GUI FLUX LoRA training tutorial. This tutorial is product of non-stop 9 days research and training. I have trained over 73 FLUX LoRA models and analyzed all to prepare this tutorial video. The research still going on and hopefully the results will be significantly improved and latest configs and findings will be shared. Please wat...
Fits worst part is reg images usage
B@Dr. Furkan Gözükara have you tried training a Lora on flux1-dev2pro.safetensors instead of the regular Flux dev model? I've read you get better results
Tye but even after i understood it, i prefer to do folder name by hand 
Tnever used reg images luckily 
Fi plan to research
Fye currently i am also doing by hand
Fi am used to it
FRunning 4 new trainings to finalize
15 img vs 256 images
both cases with Batch size 1 vs Batch size 7
15 img vs 256 images
both cases with Batch size 1 vs Batch size 7
Fso total 4 trainings
Tbtw how can i see if it actually used my captions or not?
F--debug
Fadd that to extra arg
Fadditional
PDr, can you please explain to me the logic of learning rate? is lower=training better or the other way around?
Fit is like a tool
Fyou need to have accurate size to
Fcut a pasta
Ftoo big, you cant precisely cut
Ftoo small, you cant cut enough
PSo how do I determind what I need to set it to train specific things?
Fyou cant
Fi do testing
Fi test literally every LR 
Pwhat's the default?
P0.0003?
Fdefault changes according to each config
Fbt usually for lora
F0.0001
Ffine tuning
F0.00001
Pwhat's fine tuning?
Ffully training the model
PI see
Pso 0.0001 trains more I suppose?
Fyep
F10x compared to 0.00001
Fyou can ask llms to get more idea
Flike chatgpt
DThank you. I realized now i missed that step. However, when i google enabling shared vram, i get nothing. I'm unsure how that is done
Fif you didnt disable i think it should be enabled
D
FVideoCardz.com
NVIDIA has a solution to Stable Diffusion maxing out the available memory Drivers have a new feature called “System Memory Fallback”. The NVIDIA Control Panel may still look old, but it still continues to receive feature updates. In a recent driver release, NVIDIA introduced a new option in the Control Panel tailored for consumer GeForce […]
Fok looking good should work
Dyeah it seems i have it
Falso verify this
F