LR UNET was set according to @Dr. Furkan Gözükara config file (4e-6 = 0,000004), but with AI-toolkit
LR UNET was set according to @Dr. Furkan Gözükara config file (4e-6 = 0,000004), but with AI-toolkit I have been training LORA with 1e-4 (0,0001)
Mwell yeah dreambooth you need a 1/10 off the learning rate
Mso if you're doing 1e-4 for lora you need 1e-5 for dreambooth
KYeah well... It really doesn't seem like it
M4e-6 is too low for concepts
Mheck i used 3e-5 and 5e-5
KIt has learned out of 4000 steps what the LORA learned the first 500
KI would say that @Dr. Furkan Gözükara config is way off
Mkeep in mind furkans configs are for people training
Mnot cars
KHave I missed something in his video maybe 
KYeah, but seeing how little it has learned I have a hard time thinking this would be enough for a face
M
KI guess "I'll" spend 14 more GPU hours on 0,00001
KMaybe torch 2.5.0 could help shorten the time 
NGood luck sir
Aany one has past experience in uploading custom lora to hugging face ?
Aneeded a bit help
DI made a comparison between ai-toolkit vs kohya lora training. For all the same parameters except for rank(kohya:128/128, ai-toolkit:64/64), kohya lora gives much better likeness and overall image quality. Does anyone have any observation on this or have a comment why kohya lora outperforms?
KKohya-installation according to @Dr. Furkan Gözükara = ?
KYepp... Same with Torch 2.5.0
KSo many errors... Soooo many errors 
KI hate torch and "generating weels"
KStill... Seem to be faster than 2.4.0
DDr. Gozukara, have you got any experiments on greater learning rates than 5e5 with fewer iterations? What have been your observations?
�It will outperform you are using a higher rank in kohya so it will learn more
�On how many images are you training? are you using captions? what learning rate? what network dim and alpha?
�@Dr. Furkan Gözükara How are you mentioning what blocks to train in kohya gui? I tried this but got an error -
Fyes weight 1.1 most close
Fi will post an article
Fi am aobut to post an article grid
Fdifferent workflows
Fkohya is more professionals has more experience 
Flooks like xformers requires new cuda
Fi will just remove it
Fremoved it
FPatreon
Get more from SECourses: Tutorials, Guides, Resources, Training, FLUX, MidJourney, Voice Clone, TTS, ChatGPT, GPT, LLM, Scripts by Furkan Gözü on Patreon
Fyes 2.5 really faster but not as fast as linux :/
Fit will work good on things that are not as delicate as human face
Flike styles
Fcars
Fthis is correct
Fre update your kohya
�How? I am using your installers for runpod
Freinstall
�Okay thanks
Fsingle layer quality is bad
�Okay I will test others as well. Is it possible to train multiple subjects in a checkpoint fine tune without bleeding?
Fstill bleeds
Fbut each concept can be trained on each different layer
Fprogressively