@Dr. Furkan Gözükara Now flux lora training is much slower, before I achieved 4.8 - 4.5 it/s, now I'
@Dr. Furkan Gözükara Now flux lora training is much slower, before I achieved 4.8 - 4.5 it/s, now I'm around 8.5. why is that?
Fwho knows need full debug on computer :d
Dbut you experienced the same right?
Dis something on kohya?
DIt happened and then was fixed with torch 2.5
Fnope i didnt
Ftorch 2.5 speeds up
Fyou need to run properly to no return back 2.4.1
Dso I should have the same speed 4.8 - 4.5 it/s on lora training with the current kohya version?
D
DI'm updating torch
Dmay be i was on an older version again
Dyour speed up script have pip uninstall xformers --yes
Dwhy?
Dxformers don't work with torch 2.5?
VAnyone else notice their flux fine tunes drop in likeness/quality really fast the second the subject gets far away from the camera/small? Like close up headshots look great, but a picture of the subject 20 feet away their face not only stops looking like them but starts being glitchy
VAny way to fix this?
D@Dr. Furkan Gözükara I updated torch to 2.5 but kohya installs 2.4.1 again when starting
DI fixed it --noverify
EHi everyone. Maybe this isn't news to many of you but just wanted to share my experience. I finally got fed up with windows using about 1.5gb of vram. So yesterday I bit the bullet and installed Linux, first I tried Mint but just couldn't get the Nvidia drivers to work so I switched to Pop_OS. It was a battle and so many bash commands later finally got comfyui and kohya working. And OMG! In win11 for Flux Dev Q8 gguf 50 steps at 1024 it took about 1:30 per image generation, that's after loading the models another minute+. But in Linux I'm now getting image gen in 32 seconds and models also load in just a few seconds. I'm using a 3090, 12700k, 64gb . I just wanted to share because I can't belive the difference. If you haven't tried SD with Linux and have the patience to get things working it's definitely something worth looking into.
Dthat speed is slow for windows, the speed should be similar
V@Dr. Furkan Gözükara I’m doing a flux Dora with the same dataset as the lora I showed you, quality is 1000x better.
DDora is suported in kohya?
VOnetrainer is what I’m using but I read that kohya scripts supports Dora, I can’t remember if that was a fork or implemented. I read it on either one of the kohya GitHubs.
Dthanks
D@Dr. Furkan Gözükara do you know that parameter function? I'm training flux-dev-de-distill and this model have a optimal cfg scale of 3.5, I was testing leaving it at 1 but it worked just fine.
Fnot yet sadly
Fthere is no torch 2.5 xformers yet
Fonce it arrives hopefully i will update installer
Fface inpainting
F
Fyes my starter has this
![Dazzastrous [4090]](https://cdn.discordapp.com/avatars/871389071686135838/c4a5f4d81d9eeb18d856295d692e2c07.webp?size=40)
Dfor the horse? 
Fwow nice. sadly due to shameless open ai, on windows we are missing some optimizations
Fall depends on triton
![Dazzastrous [4090]](https://cdn.discordapp.com/avatars/871389071686135838/c4a5f4d81d9eeb18d856295d692e2c07.webp?size=16)
Fhorse is good :d
Dso many trainings so little time
Fuse the config we have i tested all those :d
DJust let me know when you have concluded all your experiments doc and then I can pick one
ZHi! I ran into an issue with onetrainer can I send it here if anyone can help?
Fyou can see testing completed ones here
Fsure what is it?
ZFollowing your stable diffusion guide, I had setup the vm and everything but just running into issues launching onetrainer (it is working on vm but not on my pc)
Z@Dr. Furkan Gözükara let me know
Finstall error
Fso i would suggest this
Fon your pc