@Dr. Furkan Gözükara What to do about bleeding? I have tried lower network and lower learning rates
@Dr. Furkan Gözükara What to do about bleeding? I have tried lower network and lower learning rates but can't stop bleeding
KNo. You only specify one value for vertical AND horizontal resolution. The training is on square images. You should specify 1024 in your case. The images will be bucketed if they ar not square or if they are a different (higher) resolution than what's being trained.
K@Dr. Furkan Gözükara https://huggingface.co/blog/MonsterMMORPG/ultimate-flux-lora-training-tutorial <- Is 404
SDr Furkan there is new settinsg that improve the velocity of trianing for a 4070 ti super 16 vram actualli is 10 its i don rmeember the nomenclaure in rank 5
Fi couıldnt stop yet either
Fye they silently
Fdeleted
FMedium
I have done total 104 different LoRA trainings and compared each one of them to find the very best hyper parameters and the workflow for…
F10 second / it not bad
�Saw people talking about trainning lokr in simpletuner and that completly stops bleeding. Is it available in kohya and does swarm ui support lokr?
Fi think not
Falso their quality was subpar
Fif lokr fixes it probably fine tuning will too
�Your khoya installer and swarm ui installer for Runpod updates them automatically?
Fkohya doesnt have lokr
Fi think it is also not supported yet
Fdont know though
�@Dr. Furkan Gözükara I mean your khoya installer and swarm ui installer for Runpod updates both of them automatically or do we have to update manually?
KShit! I something have happened with my computer. Generating the same image with the same settings on my 4090 at work takes 26 sec. On my 3090 at home it never finishes because the VRAM-usage spikes
KAt work it uses 13GB VRAM and about 23GB RAM. At home it uses all 24GB VRAM and then starts with the shared memory 
KI have no clue why
KI have even installed a new Forge with the latest Torch to try, but it's the same thing
Fthey install latest version
�Great
KYeah. Of course
KMe neither
KIt's so wierd
�did you try restarting your pc?
KYes
�maybe go to the task manager and see what's eating up the memory
Syou are right DrFurkan for the quality that brings
�@Dr. Furkan Gözükara training t5 significantly increases vram usage as comapred to just the unet? Using a L40S on both the pods and getting 4.3 sec/it for the unet training and 4.75 sec/it on the t5
Zi wish i could supir images without having to use comfyui, i have a linux program called upscalayr, and it has some esrgan models, but to use supir, i would have to conver it t onnx, then NCNN format, and it probably won't even work anyways
Z@Dr. Furkan Gözükara I'd love just a simple linux or windows program you open, put your images in, and it improves using SUPIR, and also have a built in image comparison you can push back and forth
Fyes increases
Fbut speed no much impacted
Fwe have it lol 
Fi use batch mode
F
DI'm still traying to train multiple subjects in flux with no success it still beeds even with t5 and also training t5 have unespected results
Dfor example the keyword associated to one of my subjects triggers this image
Dor this
Fye bleeding is hard
Dthat's not even a human
Fthis is actually unexpected
Dcompletely random
Dhey wait is not random, is the background of one of my images.... wow
Din that photo it was me
Dthat picture is from my city
Dor a very close represntation of it