so you should see number of steps = 200 x 31 x 2
so you should see number of steps = 200 x 31 x 2
K.
Kwhat is 2 here?
KI am using 4 batch value is this okay? I mean how can we find the aproximate epochs value? Is this all trial and error process. there is no pattern?
Ksorry I am so beginer
F2x from reg images if you use
Fif you use batch size 4 use square root 4 LR
Fwhich means 2x LR
Kthat means learning rate should be 2 times ?
Fyep
K2 times default = 0.0003 x 2=0.0006
KI see, and how do you get the approximate epoch value?
Fyes
KI mean how to find the epochs value?
Kand isnt it very high learning rate?
Fwell you can use my preset it has all
Xeh whats that?
Fuse the shown values in tutorial they are working great
Xyeah I edited it, but it just wont change in UI, tried restart and install
CCould someone help me with SDXL lora training?
Fi recommend dreambooth
CI want to make fanvue AI model. Can you send me a link to your best video from this topic?
Fi dont know fanvue AI . i can give you video for flux dreambooth highest quality
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...
CThanks
PHi friends 
Tell me who can do FLUX Full Fine-Tuning as shown in this video
@Furkan Gözükara SECourses How much would such a service cost? Dataset 91 photos.
Tell me who can do FLUX Full Fine-Tuning as shown in this video @Furkan Gözükara SECourses How much would such a service cost? Dataset 91 photos.Fmessaging you
Pwhenever my model puts other people in the scene with faces visible one of them always also has my model's face even if their body is the opposite sex 
Fyes true :d
Fthis is flux bleed problem
Fvery famous
FMedium
Thoroughly experimented with Fine-Tuning / DreamBooth training of Flux-dev-de-distill, PixelWave v03, Verus Vision and base FLUX Dev model…
Ptoo funny
KAnyone have any ideas about training a Lora on a place. I mean teaching the model about a place to generate as background?
Fthe logic sounds same
Fjust ohwx and the place class
Fthen during inference prompt in details that would describe that place
Kwith 0.0003 LR adamw_8bit do you think 200 epoch for 20 image will make it over trainned?
Fi cant comment based on other configs. but my config wont
KI just found that if you put "from text file per sample" , and dont provide any caption, it still does the lora training. what will it actually do?
KI tried that and it was working without any trigger word. like textual embedding
Fit will use internal caption it has
Fso will work still true
DI've used your Flux dreambooth training presets and the results are amazing. Would training at 1280 x 1280 increase the quality even further or is that useless to try?
Dwell I'm trying it anyway lol but it's going to take awhile
Fsadly not improving
Flet me know results. but i didnt get better 
NI usually do LoRAs over full dreambooth trainings. did one LoRA at 1536x1536. on my 3090 i did 150 epochs on 20 images and it took 22 hours 
same dataset and settings at 1024x1024 had only taken 7 hours. (i think the configs and kohya itself have both been optimized a lot since then) i do feel like the 1536 LoRA is better, more detailed. but after that i stuck with 1024 - didn't feel like the improvement (it's usually subjective by then anyway with character LoRAs from only epoch 100-125 turning out awesome as well) were worth triple the training time.
same dataset and settings at 1024x1024 had only taken 7 hours. (i think the configs and kohya itself have both been optimized a lot since then) i do feel like the 1536 LoRA is better, more detailed. but after that i stuck with 1024 - didn't feel like the improvement (it's usually subjective by then anyway with character LoRAs from only epoch 100-125 turning out awesome as well) were worth triple the training time.
Fyes doesnt help much. but you can try tiled training
Fmay work for objects
