so this includes the dreambooth tutorial?
so this includes the dreambooth tutorial?
Fthis is lora. for dreambooth you load this config into dreambooth tab else is 100% same : https://www.patreon.com/posts/kohya-flux-fine-112099700
Patreon
Get more from SECourses: FLUX, Tutorials, Guides, Resources, Training, Scripts on Patreon
Fso follow this tutorial
Fwhen loading config
Finstead of lora
Fload config of dreambooth
Fdreambooth config : https://www.patreon.com/posts/kohya-flux-fine-112099700
lora config and installers (the one used in tutorial) : https://www.patreon.com/posts/110879657
lora config and installers (the one used in tutorial) : https://www.patreon.com/posts/110879657
CWill you do in future tutorial for Fine Tune / DreamBooth?.
Fyep
Fi am fully preparing it right now
Fit will show massive comparison too
Dfor those who were interested in this dreambooth-training here are some more tests. Some with reg data, some without, some with training prompt, some without anything just code. It doesn't seem to make much of a difference.
Dsimpler grids without reg images
Jsome vips are already trained in to some degree, in my experciene no reg, no prompt gives me more then good enough results. and i switched to the competitor product (fgym) because it is so easy to use 
D"no reg, no prompt" will work but change the entire model. Barack Obama will look like your trained subject.
Ji dont train known people, just ohwx works super
Dyou don't get the point, please read the thread that I linked above first.
Jits about the bleeding i know, if it works it could be usefull, but its only for onetrainer right now?
Dyes. SimpleTuner wants to implement, and I've heard kohya too, but nothing ready
Fgreat results but i couldnt get it :d
TI have a few questions. I'm now trying the DB method for flux training, no captions, 30 images, 1 repeat, 150-200 epoch about 5000-6000steps - is that too much. Also since i'm a male but i have long hair, every sample image during training shows as a women, in my case is it better to provide captions saying I'm a man? Joy caption also thinks I'm female. Also i noticed that in any of my trained/extracted lora, i can never add any other person in the picture, because they all look like me, even though I'm using a numeric trigger, and even if I import another celebrity lora, it just blends the 2 lora's together. is there no way to do an AI image of myself and my favorite celeb? ie. "photo of k3v1n with billie elish" (another lora)
Fabout second part yes it bleeds
F@dxqb found a way to lessen it on onetrainer
Fbut i couldnt make it
Fabout first part only use
Fohwx man
Fit should work with sufficient training
Fi will update patreon post with grids and my best epochs
Fbased on number of images
Fand batch size
Tso inpainting is the only way? how does it work in base flux compared to lora? because in base flux you can specify 2 embedded base celebrities, ie. john wick and taylor swift playing in a concert together.
Fthe problem is that since we train on distilled model
Fit bleeds a lot
Fbut famous people were trained before the distillation
Fso flux de-disttiled models may likely to fix this problem
Fwhen they are ready
Tthank you i understand. So for now, there is no way for me to train me and my friends and create pictures together, even with unique words in a checkpoint? could i train them all at once into a new checkpoint or would it bleed? ie. 1_k3v man, 1_fr1endone, 1_fr1endtwo (ie each friend is a concept)?
Fthere is a way
Fhave yourself in same picture
Fand train on that :d
Fthen it will work
TThank you for all of your help and community contribution, I'm at a university in Canada, and we're looking at upgrading our old Tesla T4 servers in our engineering dept, so we can do more AI research. we're a bit behind.
D@Furkan Gözükara SECourses what were your results with trying to train Flux on your reg data set? I'm attempting something similar
D@Furkan Gözükara SECourses please see here https://discord.com/channels/1102003518203756564/1149379539454140538/1294374243060027475 . I am not entirely sure this has been the reason your config didn't work, but it was the reason someone else's didn't work.
Fnever worked
LDthis is implemented in SimpleTuner now
Fchecking
Fhave you tested there?_
DNo, never used SimpleTuner so it would be a lot of effort for me to try