<@205854764540362752> a friend asked me to train using his gpu too, so is it possible in kohya or in
@Furkan Gözükara SECourses a friend asked me to train using his gpu too, so is it possible in kohya or in any other way? I got 4070, he got 4060ti.
Xand I see these checkpoint models trained on 2x A100 GPU, 4x A100 GPU... so we can combine gpus or smthing?
Fnope you cant combine
Flike that
Fon linux 2x 3090 may work for lora
Fhello again, how do I resume a Lora training in Khoya? I know how to pickup a training I left when training a finetuned checkpoint by selecting the latest saved safetensor in the " Pretrained model name or path" but I dont know hot to resume a previews Lora training , thanks for the help
WWI trained model and merge with hyper or turbo 8 step lora. The image result for 8 step for normal gen is ok but the upscale quality is worst than normal
WI wonder if i train on an already merged hyper or turbo does image will be better or not
Fnope i havent
YYSometimes it messes up with eyes looking direction
YWhat do you think ?
Fi skip in some poses
Fif it generates too close
�If my pics are jpg, should they be converted to png? Which tool should I use if I have a jpg file with say, 300 X 300 px to make it a good training image l?
�
F300x300 is terrible
Fjpg png convert doesnt matter
Fbut if original image png better
�ok thank you. @Furkan Gözükara SECourses I am just about to start dreambooth training, and I want the best quality. I heard you make a note that batch 1 48GB (using a6000) actually yields better quality than batch 7, so the only advantage with batch 7 is the speed. Would you recommend batch 1 then if I want the best quality?
�I am using 66 training images. I went for 125 epochs and save every 25 epoch.
�ok trying out batch 7 first as you suggested, if quality is not good enough, I might run batch 1 later. By the way, Why either 15 or 256 images, is that some sort of magic numbers for fine-tuning? 
Fyep batch size 1
Fi recommend
Fnope it was just a big comparison
Fso that you can know between both works great :d
F256 too many but still working
Fwith same config
WWhat's a good way to test out different checkpoints from a STYLE-BASED finetune? Same seed? poses?
all of my finetunes look too good.
all of my finetunes look too good.
Fdifferent prompts
Fsame seed
Fye usually all looks good
Fwith flux 
Wdifferent 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?