different prompts using the same seed?????
different prompts using the same seed?????
W(I mean SDXL)
Fyes
Fnice sucess then
WI must thank you. i used your tutorial to finetune SDXL using a very specific style. (400 training images)
but between epochs 75 - 150, they all look good
but between epochs 75 - 150, they all look good
W@Furkan Gözükara SECourses
I have trained a finetuned SDXL checkpoint to learn a specific style. The results are excellent.
Now, I would like to finetune that same stylized checkpoint to learn a specific character. Then I will extract it to a LORA.
The character is a female demon. But the training images (40 of them) are in various styles such as 3D, anime style, cartoon style.
If I use the caption "ohwx 1girl" or "ohwx woman", I am afraid that character will OVERWRITE the style of the finetune that I want to keep.
How do I caption the character so that it does not overwrite the style?
I have trained a finetuned SDXL checkpoint to learn a specific style. The results are excellent.
Now, I would like to finetune that same stylized checkpoint to learn a specific character. Then I will extract it to a LORA.
The character is a female demon. But the training images (40 of them) are in various styles such as 3D, anime style, cartoon style.
If I use the caption "ohwx 1girl" or "ohwx woman", I am afraid that character will OVERWRITE the style of the finetune that I want to keep.
How do I caption the character so that it does not overwrite the style?
�Can't you just avoid the 1girl and woman, and just caption "ohwxgirl", since 1girl and woman are widely recognized tags in any model.
�I did a character finetune, and noticed that almost all training images had ponytail hairstyle. I manage to produce some images without the ponytail, like prompting "messy hair", and even "no ponytail", but the latter didnt really work, haha 
Fmaybe ohwx character
Fi dont know you need to test
CDr. Furkan. What config you can recommend for me to do fastest way model of face. Not must be a perfect, Priority is time to train on single rtx 4090
Clora probably as dreambox longer
Cwhich one i should choose >
Fyou want lora right?
F
Fit should be faster than 4 second / it
Ffor you
Flike 3 second maybe 2.5
CI did that. Shared video memory should be used ? Its look like that:
C281.40s/it
C
CI think something is wrong
CI reinstalled everything again. Now I think its ok
C
Fnow this is a good speed
CIts possible train on rtx 4090 and 64gb ram using dreambox ? or no way as too slow ?
Fdreambox?
CDreamBooth
CLok
CXd
Fyes of course you can train even faster than these speeds
F
WFnew for both check speeds
Wah ok
Wbut base on your config if I want to get the best quality lora with best speed it is faster to train dreambooth and extract
Wand training time still better than train lora
Wonly down side is disk space
CSo at the moment in my situation Lora training is about 3.58s/it, but if I use DreamBooth instead TIER 1 it will be about 7.3s/it??? as I can see on above picture. So double the time. It's worth you think?. Regarding quality?.
Wtier 1 in dreambooth is different than tier 1 in lora. In lora the rank you get is 128, but in dreambooth I get the maximum rank is 640
�With 60 training pics for character, is 200 epochs and save every 25 a good setting? I don't think you changed anything about learning rate and other parameters when I watched your tutorial video @Furkan Gözükara SECourses , just use config batch 1? I'm gonna use a80 or h100 later tonight . Want to complete it as fast as possible, with highest possible quality.
COh my God. My computer froze at 48% of the Lora training. Can I somehow resume the training? Or do I have to start over?
CNow i know we need MARK some option in Koya to be able later resume training
CUnder PArameters - Advence
C
CYou should mention about this Boss.
Fyou can continue from last checkpoint lora too
F
Ffor batch size 1 L40S is good choice others are not worth very much