This just keeps getting better and better 😀
This just keeps getting better and better 
Fye really amazing results
Fbest checkpoints will clash 
Fi am generating grids right now
DI've got a feeling I'm going to run out of space on massed compute lol. Can I move the completed checkpoints to drive and delete them while the training is ongoing?
F
DHow things started
Fnoting the best checkpoints
Fye when i look bad the resemblance was too bad :d
DFlux has spoilt us all lol
Ftrue
Fnow sd 3.1 has to be good
DHow many epochs did you train for 256 image BS7 (fine-tune)?
DI have 225 imgs & I'm now saving every 2 epoch 'cuz it overtrains super fast
Fbest one is 50 epoch
Fit sounds your LR too high
For images are too duplicate :d
DUsing 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