Fok lets say 4 at worst
Fso 25 images with lets say 140 epoch
F25 * 140 * 2 = 7000 steps
Fso it would be 7000 * 4 / 60 / 60 = 7.8 hours
NOvernight it is, then! Thanks for doing the math for me. I can do the math, I just don't enjoy the process, lol.
NAlthough looking at cmd, it looks like I'm averaging around 2s/it - so maybe if I'm lucky, around 4 hours
NSo I stopped the training at 3100 and tested the saved model, and if I use all the common tags from the training in the same prompt, I get a pretty damned good result. But if I remove all or even just some of those common tags, or if I try to use any kind of creative prompt (like "sitting in a golden throne wearing golden armor"), the face likeness goes away.
Frecording onetrainer tutorial already over 2 hours
Fdid you train with captions?
FPatreon
Get more from SECourses: Tutorials, Guides, Resources, Training, MidJourney, Voice Clone, TTS, ChatGPT, GPT, LLM, Scripts by Furkan Gözükara on Patreon
NYes, that means the model you're using for inference of that word "boob" is still trained "stronger" than your LoRA concept. If you're training say the concept "girlfriend woman" with captions on your dataset you could leave out any reference to breasts. However it may make your LoRA less flexible. You could also experiment with doing the caption dropout option (available in Kohya) or for an experiment train your LoRA with no captions and see if the accuracy increases...
Chello i have a question
i have 2000 reg images
which should i use？
30 images 1 reg
or
30 images 30 reg
i have 2000 reg images
which should i use？
30 images 1 reg
or
30 images 30 reg
NAhhh, that makes sense! I created the training data before watching the tutorial, so I forgot that the caption text was included in the folder with the training images already. Damn it, back to the drawing board, lol.
N@Dr. Furkan Gözükara Someone recomended removing backgrounds for training data images, do you agree with them? I can do that pretty easily.
NOr I can use the tool to add the masks
Nlike this
EI can chime in on that a bit. Personally, that gives me disastrous results, but give it a shot if you'd like 
Fyes
Fstill recording and tutorial is now over 3 hours. this tutorial actually a standalone full course haha 
Fother than introduction here the tutorial durations :d onetrainer
Fi need to record introduction and edit it now
EAllah razı olsun hocam!!!
Fgood day / night
ESeriously though you’re probably sick of me saying this over and over but I and I’m sure this community is very thankful for everything you do. I’ve learned a ton here.
EI don’t know when you sleep.
ELooks like you do once in a while 
Ado you create samples during training? This can help figure out where it is going wrong. I usually use very specific sampling prompts to see if:
if you for example train a specific man, like tom hanks or so, your model should be able to display your concept like it could with your class "man"
so tom hanks in a black suit should look the same as man in a black suit, just with the facial and body features of tom hanks
- my concept bleeds into other concepts
- see if it is flexible on different poses and so on.
if you for example train a specific man, like tom hanks or so, your model should be able to display your concept like it could with your class "man"
so tom hanks in a black suit should look the same as man in a black suit, just with the facial and body features of tom hanks
Athats very difficult to achieve, but once you get a hang of it, you will get good results
MAny way in Kohya to NOT create checkpoints in the first N steps? Like when I train 5k steps and save 10 checkpoints (that means every 500 steps) - usually the first 3 or 4 checkpoints always look bad, so I'd like to exclude them from saving. So only start with Checkpoint saving from step 2000 onwards
EDIT: I Know I can simply delete the afterwards
EDIT: I Know I can simply delete the afterwards
Fand when i try my wife dont let me sleep :/
Fdid you try : Save last N steps
(Optional) Save only the specified number of models (old models will be deleted)
(Optional) Save only the specified number of models (old models will be deleted)
Shey guys! im having a issue while training a lora . it always gives me 2 faces and i dont know why. my training images are good and even the captioning. but still im getting 2 faces. i trained it on koyhaa. can someone help me, i used majicMIX realistic 麦橘写实 for base model
Fvery possibly wrong resolution training
Falso lora is inferior
Fwhat is your gpu?
S3060 rtx
Fok you have 12 gb gpu
Fyou can do onetrainer full fine tuning of SDXL
Fi recorded video and will post hopefully
Fyou can waitit
For you can use our already shared configs
FFSthank you so much, you are the best!
Sso all my training images should be the same pixel length and width? so 1024 x 1024?
Fthat is more preffered way
Kwhat is the correct c++ tools to install again before instant ID
Kdo i get from microsoft
KVisual Studio
Download Visual Studio IDE or VS Code for free. Try out Visual Studio Professional or Enterprise editions on Windows, Mac.
Kthis site ?
