is 1000 too many images for training a style?
is 1000 too many images for training a style?
Fnope better
Fas long as dataset is good
Ghow about 2000?
Gor 5000?
Fmore better
Fbut dataset quality matter too
Gso I should do all 10,000
Gthen
Gwhat you mean dataset?
Gand why is Epoch 200 the standard? 100? 300 better?
F1 : it can cause overtrain and overfit - thus degrade in quality
F2 : it makes huge difference since dataset size is different. more better if dataset quality is better top notch
F200 epoch is set usually for training a person
Gso you recommend I train 10,000 images instead of 1000 right? but it wont overtrain? like you are mentioning
Fyes but as i said
Fdataset matters
Gwhats that?
Gthe quality of the images?
Frestart computer reinstall
Fif error remains disable antivirus etc
FYouTubeSECourses
RunPod: https://bit.ly/RunPodIO. Discord : https://bit.ly/SECoursesDiscord. Get your own #Midjourney level model for free via Style Teaching. If I have been of assistance to you and you would like to show your support for my work, please consider becoming a patron on 
https://www.patreon.com/SECourses
Playlist of #StableDiffusion Tutorials, Au...
https://www.patreon.com/SECoursesPlaylist of #StableDiffusion Tutorials, Au...
Fthe logic is same
Fit uses more vram 
what gpu u have?
what gpu u have?GSo I should do the 10K images over the 1K then right? So final question is how many days would it take to train? And whats the fastest VPS you recommend? I want to do this ASAP
GIll pay for 4 or 8 GPU rental
TI’m using a 4090
FMassed compute go with 4x gpu
F1.25 usd hour
GHow do I calculate the hours it will take?
FBut I suggest you to get a private lecture before such big traininh
Gwhats that
FI don't know if work on that
TIt does work, just need the right batch size
FI give 1 to 1 lecture
FBatch size 1 best
TFor quality I agree
FBatch size 2 made like %25 improvement
FRest didn't do
FI tasted on a6000
Geven batch size 4 works on A6000 bros I tested it today
TThanks - will keep that in mind! Yeah it would be awesome if you could make a config for prodigy, I was able to train the darkest dungeon sdxl Lora in probably 1/10th of the time
GRANK 5
TI will have a look to see if I can find my old config
GI got it to over 30+ iterations
Git has a lot of VRAM i figured what the hell and tried it
TNice one man
TFound my old prodigy config - will do some testing with flux dev and let you know if it's any good. Note I'm training a style, so the dims will be higher
Gbrother i want to do that too, how many images will u train?
Gplease do share infos
T350 images in dataset roughly
