Software Engineering Courses (SECourses)•10mo ago

hi doc. Im a new member, and im new for this fine tuning. Im having an error, I think it's probably

hi doc. Im a new member, and im new for this fine tuning. Im having an error, I think it's probably about oom, but I want to make sure its not cudnn/cuda toolkit/visual studio problem. Is there a way to do finetuning in local machine even with 32 gb phyusical ram?
im using rtx3060 12gb vram with 32gb physical ram

flux_cmd_history.txt49.46KB

NNeyo Ney hi doc. Im a new member, and im new for this fine tuning. Im having an error, I ...

Furkan Gözükara SECourses•2/27/25, 1:32 AM

hi welcome

Furkan Gözükara SECourses•2/27/25, 1:32 AM

it is all about 32 gb ram

Furkan Gözükara SECourses•2/27/25, 1:33 AM

upgrade to 64 gb and i give 100% guarantee it will work

Furkan Gözükara SECourses•2/27/25, 1:33 AM

this happens because these models are huge

Furkan Gözükara SECourses•2/27/25, 1:33 AM

so we use block swapping (swap between RAM and GPU)

Furkan Gözükara SECourses•2/27/25, 1:33 AM

and it need actual phyiscal RAM

Furkan Gözükara SECourses•2/27/25, 1:34 AM

i got to sleep now

Neyo NeyOP•2/27/25, 1:34 AM

haha, welp time to use cloud machine i guess. Thanks doc!

NNeyo Ney haha, welp time to use cloud machine i guess. Thanks doc!😊

Furkan Gözükara SECourses•2/27/25, 1:34 AM

you are welcome. massed compute great

Furkan Gözükara SECourses•2/27/25, 1:34 AM

really fast

Furkan Gözükara SECourses•2/27/25, 1:35 AM

wan 2.1 tutorial i have to edit tomorrow

Neyo NeyOP•2/27/25, 1:37 AM

yesss, image to video is going to be great! I'm excited to try that too

FFurkan Gözükara SECourses yes but slow

sergio_gonzo•2/27/25, 4:59 AM

DrFurkan do you think the 5070 ti super could be better in this task? i mean for the increase of ai procesor?

FFurkan Gözükara SECourses wan 2.1 tutorial i have to edit tomorrow 😄

Neuromasters•2/27/25, 8:09 AM

Oh, it's the long-awaited video

Ssergio_gonzo DrFurkan do you think the 5070 ti super could be better in this task? i mean for...

Furkan Gözükara SECourses•2/27/25, 9:17 AM

compared to which gpu?

NNeyo Ney yesss, image to video is going to be great! I'm excited to try that too

Furkan Gözükara SECourses•2/27/25, 9:17 AM

yep really good

Furkan Gözükara SECourses•2/27/25, 10:21 AM

yes fixed video error :d

Furkan Gözükara SECourses•2/27/25, 11:14 AM

FP8 now works

Furkan Gözükara SECourses•2/27/25, 11:14 AM

https://www.patreon.com/posts/123105403

Patreon

Wan 2.1 Ultra Advanced Gradio APP for - Works as low as 4GB VRAM - ...

Get more from SECourses: FLUX, Tutorials, Guides, Resources, Training, Scripts on Patreon

Furkan Gözükara SECourses•2/27/25, 11:14 AM

FFurkan Gözükara SECourses yolo format : <segment:yolo-face_yolov9c.pt-1,0.7,0.5>photograph of ohwx man

TrumpYouAll•2/27/25, 11:33 AM

Sorry @Dr. Furkan Gözükara the 5090 patch does work sometimes while doesn't work the other time (not stable)
However, I would like to ask if you can point to me where I can enable Yoloface in the SwarmUI ? I remember I saw one of those vidoes before but I forgot where I can enable it after I have dowloaded the model.

Thanks in adavance, my AI Image Generation Master

TTrumpYouAll Sorry @Dr. Furkan Gözükara the 5090 patch does work sometimes while doesn't work...

Furkan Gözükara SECourses•2/27/25, 11:45 AM

ye it is made by comfyui maybe i can make a better version now since we got nightly torch

Furkan Gözükara SECourses•2/27/25, 11:45 AM

using is easy

Furkan Gözükara SECourses•2/27/25, 11:45 AM

after downloading into yolov8 folder

Furkan Gözükara SECourses•2/27/25, 11:46 AM

<segment:yolo-face_yolov9c.pt-1,0.7,0.5>photograph of ohwx man

Furkan Gözükara SECourses•2/27/25, 11:46 AM

this will inpaint 1st face

Furkan Gözükara SECourses•2/27/25, 11:46 AM

you can select order of faces

Furkan Gözükara SECourses•2/27/25, 11:46 AM

pt-1 means first face

Furkan Gözükara SECourses•2/27/25, 11:46 AM

<segment:yolo-face_yolov9c.pt,0.7,0.5> = all faces

FFurkan Gözükara SECourses ye it is made by comfyui maybe i can make a better version now since we got nigh...

TrumpYouAll•2/27/25, 11:47 AM

so, among all advanced options, I go to 'inpaint' to check out the options of yoloface? Thanks !

TTrumpYouAll so, among all advanced options, I go to 'inpaint' to check out the options of yo...

Furkan Gözükara SECourses•2/27/25, 11:47 AM

this is not inpainting - this happens during generation

Furkan Gözükara SECourses•2/27/25, 11:47 AM

for inpainting i have tutorial already let me show

Furkan Gözükara SECourses•2/27/25, 11:48 AM

https://youtu.be/HKX8_F1Er_w

YouTubeSECourses

Zero to Hero Stable Diffusion 3 Tutorial with Amazing SwarmUI SD We...

Do not skip any part of this tutorial to master how to use Stable Diffusion 3 (SD3) with the most advanced generative AI open source APP SwarmUI. Automatic1111 SD Web UI or Fooocus are not supporting the #SD3 yet. Therefore, I am starting to make tutorials for SwarmUI as well. #StableSwarmUI is officially developed by the StabilityAI and your m...

Furkan Gözükara SECourses•2/27/25, 11:48 AM

1:08:43 How to use edit image / inpainting
1:10:38 How to use amazing segmentation feature to automatically inpaint any part of images
1:15:55 How to use segmentation on existing images for inpainting and get perfect results with different seeds

FFurkan Gözükara SECourses this is not inpainting - this happens during generation

TrumpYouAll•2/27/25, 11:49 AM

no no no, please, I only want yoloface, I just wanna know where to go so as to enable Yoloface

TrumpYouAll•2/27/25, 11:49 AM

Thanks @Dr. Furkan Gözükara !

TTrumpYouAll no no no, please, I only want yoloface, I just wanna know where to go so as to e...

Furkan Gözükara SECourses•2/27/25, 11:51 AM

you dont enable that way

Furkan Gözükara SECourses•2/27/25, 11:51 AM

i recommend watch tutorials :d

TrumpYouAll•2/27/25, 11:51 AM

okay, I will watch it again, Master @Dr. Furkan Gözükara

AiInfluence•2/27/25, 11:57 AM

@Dr. Furkan Gözükara I can't seem to understand the logic for segmentation of face >=2 with yolo . What's the command line again? for 2 face left to right

AAiInfluence @Dr. Furkan Gözükara I can't seem to understand the logic for segmentation of fa...

Furkan Gözükara SECourses•2/27/25, 12:03 PM

you have to write twice

Furkan Gözükara SECourses•2/27/25, 12:03 PM

i think

Furkan Gözükara SECourses•2/27/25, 12:03 PM

<segment:yolo-face_yolov9c.pt-1,0.7,0.5>photograph of ohwx man <segment:yolo-face_yolov9c.pt-2,0.7,0.5>photograph of ohwx man

AiInfluence•2/27/25, 12:12 PM

so generate one picture

AiInfluence•2/27/25, 12:12 PM

and then write yolo 2 times?

AiInfluence•2/27/25, 12:12 PM

so 3 picture in total to get what I want

AAiInfluence so 3 picture in total to get what I want

Furkan Gözükara SECourses•2/27/25, 2:12 PM

i didnt get what you mean

Furkan Gözükara SECourses•2/27/25, 2:12 PM

if anyone has good wan 2.1 video please send me

Furkan Gözükara SECourses•2/27/25, 2:12 PM

i can put to tutorial

HRK•2/27/25, 2:49 PM

Hey all, I've played around to try training loras on Wan, I cannot get Diffusion-pipe to work, it never finds the config file, and i've tried DiffSynth, which works but only accepts videos.

I wondered, is there a 3rd alternative ? And as it seems i'm currently stuck with DiffSynth, we do agree the dataset must be videos max 720x1280 of 81 frames at 16fps, right ?

hi doc. Im a new member, and im new for this fine tuning. Im having an error, I think it's probably

Similar Threads