Using 4e-6, or 0.000004, which was recommended. But hey, 50*256 would be 12,800 steps! Do you mean B
Using 4e-6, or 0.000004, which was recommended. But hey, 50*256 would be 12,800 steps! Do you mean BS7 would mean 12,800/7 ~ 1,828 steps approx?
Fi will publish my grids generating them
Falso my findings
DNow tuning two checkpoints side by side, one on flux_dev, another on dev_de_distill.
DThe de-distill trains a tad bit faster it seems.
DThis is what I made earlier with Flux Pro 1.1
DSame prompt for Flux_dev:
D
DWish we had access to Pro as well. 
DI'm training a lora tree people 2 same class 1 different class with regularization on flux-dev-de-distill, lets see if regularization images works with flux-dev-de-distill
Dthe regularization are person class
Dthe bleeding between subjects was fixed with flux-dev-de-distill but idk yet if works with regularization
D@Dr. Furkan Gözükara flux-dev-de-distill what I saw was that at 30 epoch's the resemblances was reduced with regularization images, lets see if a full 160 epochs fixes that.
DHow many images are there in your dataset?
DWhat tool do you use to make this curve? I don't let logs save at all lol. Perhaps I should reconsider.
Djust tensorboard on kohya, 10 or 11 pictures per subject, I have a folder with real people as regularization, 2000 images different ages, genders and races
DI downloaded the regularization dataset a time ago with captions
DAwesome!
DFor me, that option says start even though the training is on 
@dsienra
@dsienra
Djust press it
Dit will start tensorboard
Dis independent of trainig
D
Djust select the current training in the bottom or enable all to compare the loss curve with past trainings
Dis just a guide
Din theory it should go down until starts overtraining and in that case it should go up again, when the training just starts the loos goes up and down, that is normal on the first epochs, but overall the graphic should go down during the entire training
DHello,
I am trying to follow the Patreon post on finetuning.
https://www.patreon.com/posts/huge-news-for-as-113531833
I am trying to follow the Patreon post on finetuning.
https://www.patreon.com/posts/huge-news-for-as-113531833
Patreon
Get more from SECourses: FLUX, Tutorials, Guides, Resources, Training, Scripts on Patreon
Dit says same process as lora, only different config. Do I still use the LoRa tab in the webinterface or do I use dreambooth?
Thanks
Daniel
Thanks
Daniel
DDo dreambooth
DI have a RTX 3060 and am getting ~45sec/it, which would take quite long for 9200 steps, is that normal?
Dnvitop is showing >90% GPU utilization
Fnice test
Fdreambooth tab
Frtx 3060 takes around 40 second / it in long run
DThe training was finished, resemblance is almost perfect, but it still looks a little undertrained, with regularization images it needs much more steps or increase the learning rate to get resemblance. I will resume the training from 160 repetitions per image and I will report back, there was no bleeding between the trained subjects
Fwow awesome
Fi am waiting that model to become more mature
Fwill fully test it and compare
DNice, If you have to train more than one subject it is your only choice, in my tests is superior on everything, the only problem is if you are going to do a full training the inference of the resulting model will be slower because you have to set the cfg scale to 3.5, to overcome it what can be done is to do the finetune, extract the lora and then use the resulting lora on regular flux-dev and be able to use cfg scale 1 in conjunction with distilled cfg
Fonce you use cfg > 1 = it doubles the duration of generation
Dthe quality of an extracted lora from a finetune is comparable to a finetune?
Fi made a comparison
Fbut i doubt it would work on
Fdev model
Dthe loras I'm training on flux-dev-de-distill works perfect on regular flux-dev, why the extracted lora will not work?
Dnot in the other way around the loras trained on regular flux-dev lost resemblance on flux-dev-de-distill on inference
Fwow if working then yes
