just wait till you try fine tuning
just wait till you try fine tuning
For you tried it?
CNope; I just did a LoRA with flux
Cwith my face
Cis that what you mean by fine tuning or ?
Fok then you will likem it
Ffine tune / dreambooth
Frecording tutorial now
Cniceeeeeeeee
C
Fyep
Fvideo recording over 2 hours already :d
Ccan't wait 
Fthis is like a full course tutorial haha
M@Dr. Furkan Gözükara time for you to stay away and run more tests.
lycoris training available now for kohya and he also fixed the prior preservation loss
lycoris training available now for kohya and he also fixed the prior preservation loss
Mhe will merge into the branch in a bit
Fi will more tests later i need to publish tutorial first
Frest will be only updating configs
MLycoris already looks quite good with dora on flux, so hopefully you can explore better settings when you do
XI can’t wait for this ahahah + can wait for 4K image to video!
BHello all- I am looking for help with a project relating to flux and creating seamless images. Right now, it is unable to make images that can be tiled into larger designs. If anyone is up for a project, I am willing to pay for its development.
Adr for the style, what happens if you add in like I dont know 5,000 images for the stylization then you do half that number for your character. Is that too much?
Dhttps://huggingface.co/nyanko7/flux-dev-de-distill Unet LR 0.0001 vs 0.00003 the loos curve looks so different, up 80 epochs at 0.0001 it started to overtrain, lets see now...
Dmay be 0.00003 is too low, idk
DIsn't this like, already 7.5 times higher than what the Doc recommended?
Dno
Dthis is one of the Dr. Furkan config files 3e-05=0.00003
Dthat's with the T5 options enable, may be I have to increase it to 0.00005 in this file is at that value
DOhh, I see. You're doing a lora, not a full dreambooth. My bad.
Dyes lora
DI will test a finetune in the future with flux-dev-de-distill but it uses cfg scale 3.5 that is slower, I can try to extract the lora and try it with regular flux-dev at full speed
DYes, makes sense
PTesting Style transfer function in new ui, is being born.
Dand do you recommend masked training over "normal" training?
Dalso as far as I remember your dataset is images without a detailed background anyway, right?
Njust had amazing results training a flux fine tune , thank u
Nalso how do I switch fp16 models in flux without this message
XHello, sent you a request
X@BrennenRB
XInteresting!
JI have a dataset of 25 images for this character, and I’m trying to train a LoRA for FLUX. I used the best config with Rank 4 and set the epoch to 100, which resulted in 2500 steps. However, the results from the prompt don’t look like the character I want to portray. Should I increase the epoch to 200? Also, I’m using captions generated by ChatGPT like this: 'GDZHBo_flx, a cartoon character with a large mustache and glasses, sitting with a playful expression as he appears to be gesturing something with his hands, adding a humorous and relaxed vibe.' Any advice?
JThis is an example of the results I’m getting after training the character. The outputs don’t quite match the character I want
DThis works (Saved me tons of space on home PC):
You should be able to change ModelRoot to whatever place on your system you have your models stored and, if the subdirs vary from what SwarmUI uses, modify them here. That should capture unet. It will look in {ModelRoot}/unet or {ModelRoot}/diffusion_models as needed.
You should be able to change ModelRoot to whatever place on your system you have your models stored and, if the subdirs vary from what SwarmUI uses, modify them here. That should capture unet. It will look in {ModelRoot}/unet or {ModelRoot}/diffusion_models as needed.
Fsounds too much but can be tested
Fnice
Fi dont recommend
Fget your training set better :d
Fbut i plan to test
Fon flux too
Fyou can convert model to fp8
FPatreon
Get more from SECourses: FLUX, Tutorials, Guides, Resources, Training, Scripts on Patreon