Software Engineering Courses (SECourses)•3y ago

Very much a novice -- I was watching your comprehensive tutorial on setting up ComfyUI on RunPod. Th

Very much a novice -- I was watching your comprehensive tutorial on setting up ComfyUI on RunPod. There is now a template for: RunPod SD Comfy UI. To follow your tutorials, do I need to do anything other than save the checkpoints to the proper folder in the workspace?

DDetailOriented Very much a novice -- I was watching your comprehensive tutorial on setting up C...

Furkan Gözükara SECourses•11/30/23, 1:07 AM

if template working probably you dont need

Furkan Gözükara SECourses•11/30/23, 1:07 AM

but templates usually dont get updated

Furkan Gözükara SECourses•11/30/23, 1:08 AM

frequently

Furkan Gözükara SECourses•11/30/23, 1:38 AM

https://www.linkedin.com/posts/furkangozukara_started-3-massive-stable-diffusion-xl-sdxl-activity-7135804057180327936-BgLR?utm_source=share&utm_medium=member_desktop

Furkan Gözükara on LinkedIn: Started 3 massive Stable Diffusion XL ...

Started 3 massive Stable Diffusion XL (SDXL) DreamBooth trainings for a client.

I am trying to train a certain style drawings. Each training testing different…

Furkan Gözükara SECourses•11/30/23, 1:39 AM

doing a massive training

AIGambino•11/30/23, 2:36 AM

do we have to edit each of these or can I delete all but one and just have it as my 1024x1024?

FFurkan Gözükara SECourses actually when I tested before they did training on 512x512 haha

r1•11/30/23, 2:37 AM

Do they still? It mentions cropping 512 still down to

AIGambino•11/30/23, 3:02 AM

Weird, it turns my images sideways and crops into the face for some reaosn, no idea why

AIGambino•11/30/23, 3:56 AM

Any idea when why when I loaded the 24gb text json it doesn't autofill the additional params? usually this is longer I think

DR.Siva•11/30/23, 6:09 AM

can you run animatediff on 3080 10 gb ?

MrJoozy•11/30/23, 12:54 PM

would you say its better to do dreambooth training via the extension on automatic1111 or do it on khoya?

AAIGambino do we have to edit each of these or can I delete all but one and just have it as...

Furkan Gözükara SECourses•11/30/23, 1:35 PM

you can delete that you dont need

Rr1 Do they still? It mentions cropping 512 still down to

Furkan Gözükara SECourses•11/30/23, 1:35 PM

i dont know didnt test recently

AAIGambino Any idea when why when I loaded the 24gb text json it doesn't autofill the addit...

Furkan Gözükara SECourses•11/30/23, 1:35 PM

i see auto filled

DDR.Siva can you run animatediff on 3080 10 gb ?

Furkan Gözükara SECourses•11/30/23, 1:36 PM

i am yet to explore animate diff

DR.Siva•11/30/23, 1:54 PM

it produced a bujnch of pics which were related but not worthy to be made into gif , if thats the output.. have to explore. The prompr length also seems to matter..

FFurkan Gözükara SECourses https://www.linkedin.com/posts/furkangozukara_i-just-had-a-client-meeting-explai...

wantedrbk•11/30/23, 2:02 PM

best hyper parametrs , its about these you posted on patreon 24GB_TextEncoder kohya ? , and how many images did you select for training, and repeats while using class images

wantedrbk•11/30/23, 2:05 PM

if im gonna use 3 4 gpus , i also need consider about for choosing right number of repeats , as u said , if i have two gpus need to devide it on number of gpus

Mmikemenders Now tell me why you use so many reps and spend hours training when it was done i...

aligg73•11/30/23, 2:14 PM

Very inspiring, have you considered checkpoint training with EveryDream2 instead of LoRa...and watch these same parameters? Just wondering whether this could lead to even better results. Although I agree with you, the quick turnaround of LoRa training is great from a feedback cycle point of view.

Wwantedrbk best hyper parametrs , its about these you posted on patreon 24GB_TextEncoder k...

Furkan Gözükara SECourses•11/30/23, 2:31 PM

i used 14 images

Wwantedrbk if im gonna use 3 4 gpus , i also need consider about for choosing right number ...

Furkan Gözükara SECourses•11/30/23, 2:32 PM

multiple gpu means increased batch size

Furkan Gözükara SECourses•11/30/23, 2:32 PM

so 2 gpu will make it batch size 2. so you should halve the number of steps

Furkan Gözükara SECourses•11/30/23, 2:32 PM

yes that training done with 24gb config on patreon

Furkan Gözükara SECourses•11/30/23, 2:32 PM

https://www.patreon.com/posts/very-best-for-of-89213064

Furkan Gözükara SECourses•11/30/23, 2:33 PM

24GB_TextEncoder.json

FFurkan Gözükara SECourses multiple gpu means increased batch size

wantedrbk•11/30/23, 3:02 PM

Thanks , Repeats should be around 160 for sdxl , I remember for 1.5 it’s easy to overtrain and 25-40 was okay

DR.Siva•11/30/23, 3:23 PM

this time , the image creation needed very little effort to bring the face output. Using correct , HQ face images , makes lora training much easier.

AIGambino•11/30/23, 3:54 PM

Do we use extract faces or resizer?

AIGambino•11/30/23, 4:24 PM

is this correct? I just want to do 1024x1024

Aaligg73 Very inspiring, have you considered checkpoint training with EveryDream2 instead...

mikemenders•11/30/23, 5:43 PM

I find the big model training unnecessary. I'd only do it if I really wanted to make a new model, but that would require millions of photos, and I only do DreamBooth very rarely (for example for a pose that no model can do by default, like a full undereye). For everything else, I have Lora, which is fast, perfect for me, and the quality is absolutely comparable to a DB model, plus I can put it on top of any model, mix it with other Lora.

AAIGambino is this correct? I just want to do 1024x1024

mikemenders•11/30/23, 5:48 PM

Need only one DATA array only for all size what you need, example:

DATA = [
    ((512, 512), r"G:\man dataset\new_cropped\512x512"),
    ((768, 768), r"G:\man dataset\new_cropped\768x768"),
    ((1024, 1024), r"G:\man dataset\new_cropped\1024x1024")
]

DATA = [
    ((512, 512), r"G:\man dataset\new_cropped\512x512"),
    ((768, 768), r"G:\man dataset\new_cropped\768x768"),
    ((1024, 1024), r"G:\man dataset\new_cropped\1024x1024")
]

AIGambino•11/30/23, 5:49 PM

Can I just delete the second data = [] one?

mikemenders•11/30/23, 5:49 PM

yes

mikemenders•11/30/23, 5:50 PM

last comma no need

AIGambino•11/30/23, 5:51 PM

its being strange

AIGambino•11/30/23, 5:51 PM

cropping and rotating

AIGambino•11/30/23, 5:52 PM

and also its 512?

mikemenders•11/30/23, 5:53 PM

Yes, it's 512. Have you used the Yolo script before?

AIGambino•11/30/23, 5:54 PM

nope

mikemenders•11/30/23, 5:54 PM

First is the Yolo script, it cuts the person. Then select the best images by hand or with CompreFace and then use this cropping tool.

AIGambino•11/30/23, 5:55 PM

whats extract_faces for?

mikemenders•11/30/23, 5:56 PM

There is a Yolo script under 30th october update:
https://www.patreon.com/posts/sota-subject-and-88391247

mikemenders•11/30/23, 5:56 PM

"Yolo v7 based cropper script updated and now works much better."

mikemenders•11/30/23, 5:57 PM

or Auto cropper (that's same)

mikemenders•11/30/23, 5:57 PM

Under this section found newer version on same patreon link:
How To Use Subject Cropper

mikemenders•11/30/23, 5:58 PM

I use (1536, 1536) aspect ratio only, because need square crop later and this size is largest. No need other ratios from there

mikemenders•11/30/23, 6:00 PM

cropper_v7.py, line 13

mikemenders•11/30/23, 6:00 PM

Once you're done cutting and sorting, then use the resizer and it will cut it out really well.

Mishroom•11/30/23, 6:01 PM

Hi! I have some issues with Dreambooth Kohya, I tried to start learning but it stopped because of ‘ Doesn’t exist img folder’. I upload train dataset in workspace and pointed in dreambooth. It has happened on Runpod

Mmikemenders There is a Yolo script under 30th october update: https://www.patreon.com/posts/...

AIGambino•11/30/23, 6:02 PM

So I have the yolo v7 in its completely own folder?

Very much a novice -- I was watching your comprehensive tutorial on setting up ComfyUI on RunPod. Th

Similar Threads

Similar Threads

Similar Threads