Software Engineering Courses (SECourses)•6mo ago

i changed to 48 but stills runs at the same speed. ae = "X:/AI/Kohya/ae.safetensors" do you see anyt

i changed to 48 but stills runs at the same speed.
ae = "X:/AI/Kohya/ae.safetensors" do you see anything wrong with the toml?
I really appreciate your help
blocks_to_swap = 0
bucket_no_upscale = true
bucket_reso_steps = 64
cache_latents = true
cache_latents_to_disk = true
cache_text_encoder_outputs = true
cache_text_encoder_outputs_to_disk = true
caption_dropout_every_n_epochs = 0
caption_dropout_rate = 0

K4bronskyOP•7/14/25, 11:38 AM

single_blocks_to_swap = 0
t5xxl = "X:/AI/Kohya/t5xxl_fp16.safetensors"
t5xxl_max_token_length = 512
timestep_sampling = "sigmoid"
train_batch_size = 1
train_blocks = "all"
train_data_dir = "X:\AI\Kohya\SwarmUI_Model_Downloader_v54\SwarmUI\Models\diffusion_models\img"
vae_batch_size = 4
wandb_run_name = "miakillamodel"
xformers = true

KK4bronsky i changed to 48 but stills runs at the same speed. ae = "X:/AI/Kohya/ae.safetens...

Furkan Gözükara SECourses•7/14/25, 11:39 AM

wait at least 100 steps

Furkan Gözükara SECourses•7/14/25, 11:39 AM

also show me nvitop output

FFurkan Gözükara SECourses wait at least 100 steps

K4bronskyOP•7/14/25, 11:42 AM

KK4bronsky Click to see attachment

Furkan Gözükara SECourses•7/14/25, 11:52 AM

yes looking accurate

Furkan Gözükara SECourses•7/14/25, 11:52 AM

what is speed?

FFurkan Gözükara SECourses yes looking accurate

K4bronskyOP•7/14/25, 11:54 AM

4.22

KK4bronsky 4.22

Furkan Gözükara SECourses•7/14/25, 12:05 PM

yes a little bit slow

Furkan Gözükara SECourses•7/14/25, 12:05 PM

i dont know what causes exactly but kohya working slower than before

Furkan Gözükara SECourses•7/14/25, 12:05 PM

he made something worse

Furkan Gözükara SECourses•7/14/25, 12:05 PM

we cant fully utilize gpu for some reason

Furkan Gözükara SECourses•7/14/25, 12:05 PM

FFurkan Gözükara SECourses yes a little bit slow

K4bronskyOP•7/14/25, 12:11 PM

ok, at least i know Im on the right path, thanks so much

KK4bronsky ok, at least i know Im on the right path, thanks so much

Furkan Gözükara SECourses•7/14/25, 12:15 PM

you are welcome

KK4bronsky ok, at least i know Im on the right path, thanks so much

Furkan Gözükara SECourses•7/14/25, 2:55 PM

10 epoch is too low

Furkan Gözükara SECourses•7/14/25, 2:55 PM

how many images you have in dataset?

FFurkan Gözükara SECourses you are welcome

K4bronskyOP•7/14/25, 2:56 PM

yeah i paused just to test, i have 171 faces with same hairstyle different emotions, 53 body different poses, a bit of different hair styles

KK4bronsky yeah i paused just to test, i have 171 faces with same hairstyle different emoti...

Furkan Gözükara SECourses•7/14/25, 2:56 PM

what you want to teach?

FFurkan Gözükara SECourses what you want to teach?

K4bronskyOP•7/14/25, 2:58 PM

a person, trying to keep the same hairstyle, but also the option to change the hairstyle with prompts

KK4bronsky a person, trying to keep the same hairstyle, but also the option to change the h...

Furkan Gözükara SECourses•7/14/25, 2:59 PM

ok it is easy. 171 images are all from same person right?

Furkan Gözükara SECourses•7/14/25, 2:59 PM

a bit of different hair styles are ok

Furkan Gözükara SECourses•7/14/25, 2:59 PM

so what you should do is

K4bronskyOP•7/14/25, 2:59 PM

yeah mostly same hair cut, the ones with full body have different haircuts

Furkan Gözükara SECourses•7/14/25, 2:59 PM

just train with ohwx woman

Furkan Gözükara SECourses•7/14/25, 2:59 PM

then when prompting

Furkan Gözükara SECourses•7/14/25, 2:59 PM

describe the hair style in details

Furkan Gözükara SECourses•7/14/25, 2:59 PM

and it should work 95%+

FFurkan Gözükara SECourses just train with ohwx woman

K4bronskyOP•7/14/25, 3:00 PM

ok, ill keep training from epoch 10 forward, and ill try that in a bit, thanks so much

KK4bronsky ok, ill keep training from epoch 10 forward, and ill try that in a bit, thanks s...

Furkan Gözükara SECourses•7/14/25, 3:01 PM

you are welcome

Furkan Gözükara SECourses•7/14/25, 3:01 PM

i trained with 256 images

Furkan Gözükara SECourses•7/14/25, 3:01 PM

and 70 epoch was best

Furkan Gözükara SECourses•7/14/25, 3:01 PM

and it is excellent quality

K4bronskyOP•7/14/25, 3:32 PM

excelent, yeah thats what ill try to do

Shyam Nimmana•7/16/25, 5:28 AM

For LoRA training with 15 images and an epoch of 200 on RTXA6000, it takes around 7 hours. Shall we change the epoch value to 15 or 10? Is the caption mandatory?

SShyam Nimmana For LoRA training with 15 images and an epoch of 200 on RTXA6000, it takes aroun...

Furkan Gözükara SECourses•7/16/25, 10:48 AM

that would be undertrained

Furkan Gözükara SECourses•7/16/25, 10:49 AM

we use ohwx man as caption

Furkan Gözükara SECourses•7/16/25, 10:49 AM

i mean ohwx + class

Furkan Gözükara SECourses•7/16/25, 10:49 AM

it reads from folder name

Shyam Nimmana•7/16/25, 10:50 AM

But for lora training is 7hr mandatory?

Shyam Nimmana•7/16/25, 10:51 AM

And epoch should be 200

SShyam Nimmana But for lora training is 7hr mandatory?

Furkan Gözükara SECourses•7/16/25, 10:54 AM

yes flux is slow to train .

Furkan Gözükara SECourses•7/16/25, 10:55 AM

200 is best number for 15 images

Furkan Gözükara SECourses•7/16/25, 10:55 AM

but if you need speed

Furkan Gözükara SECourses•7/16/25, 10:55 AM

you can increae learning rate and reduce epoch

Furkan Gözükara SECourses•7/16/25, 10:55 AM

and sacrifice some quality

Shyam Nimmana•7/16/25, 10:56 AM

Ok sir

diegoarmanda•7/16/25, 2:53 PM

I have a photo with dimensions 1080 x 1920 (from TikTok). How can I make it 1024 x 1024? Can I directly follow a tutorial like in a video using the Ultimate-Batch image pre-processing tool? Do I need to check (mark) 'resize without cropping (center image and add white background)'?

Or do I need to edit it manually first using an application like Photoshop?

Ddiegoarmanda I have a photo with dimensions 1080 x 1920 (from TikTok). How can I make it 1024...

Furkan Gözükara SECourses•7/16/25, 2:58 PM

you can use this

Furkan Gözükara SECourses•7/16/25, 2:58 PM

first do 1024x1024 cropo

Furkan Gözükara SECourses•7/16/25, 2:58 PM

then resize

i changed to 48 but stills runs at the same speed. ae = "X:/AI/Kohya/ae.safetensors" do you see anyt

Similar Threads

Similar Threads

Similar Threads