Software Engineering Courses (SECourses)•10mo ago

but with cpu offloading i think should work

Furkan Gözükara SECoursesOP•3/1/25, 1:12 PM

fine on 48 gb

FFurkan Gözükara SECourses but with cpu offloading i think should work

�

𝗡𝗶𝘁𝗶𝗻 𝗣𝗮𝗿𝗲𝘃𝗮•3/1/25, 1:14 PM

I ran the installation according to their instructions on github and got cuda out of memory error. I will try the cpu offload now but not able to get their gradio running

Furkan Gözükara SECoursesOP•3/1/25, 1:16 PM

ok it is getting ready

Furkan Gözükara SECoursesOP•3/1/25, 1:16 PM

�𝗡𝗶𝘁𝗶𝗻 𝗣𝗮𝗿𝗲𝘃𝗮 I ran the installation according to their instructions on github and got cuda ou...

Furkan Gözükara SECoursesOP•3/1/25, 1:17 PM

you can ask on their github

FFurkan Gözükara SECourses you can ask on their github

�

𝗡𝗶𝘁𝗶𝗻 𝗣𝗮𝗿𝗲𝘃𝗮•3/1/25, 1:19 PM

they also have multi gpu inference

�𝗡𝗶𝘁𝗶𝗻 𝗣𝗮𝗿𝗲𝘃𝗮 they also have multi gpu inference

Furkan Gözükara SECoursesOP•3/1/25, 1:19 PM

i think not working

julius•3/1/25, 7:05 PM

@Dr. Furkan Gözükara Do you know if I wanted to do a custom setup where I have the exact programs and files installed as soon as I initialize a machine on Massedcompute, could I do that with a Docker container or something like that?

Jjulius @Dr. Furkan Gözükara Do you know if I wanted to do a custom setup where I have t...

Furkan Gözükara SECoursesOP•3/1/25, 8:02 PM

yes docker is choice

Furkan Gözükara SECoursesOP•3/1/25, 8:02 PM

i think it already supports loading custom image

Furkan Gözükara SECoursesOP•3/1/25, 8:03 PM

man family life taking so much time

i just came back to work

Furkan Gözükara SECoursesOP•3/1/25, 9:28 PM

i am adding cfg and flow shift and rife to our wan app

Furkan Gözükara SECoursesOP•3/1/25, 9:28 PM

almost done

FFurkan Gözükara SECourses fidelity is amazing image to video

masood•3/1/25, 9:31 PM

what model is this, DR?

Mmasood what model is this, DR?

Furkan Gözükara SECoursesOP•3/1/25, 9:38 PM

wan 2.1 14b image to video

Furkan Gözükara SECoursesOP•3/1/25, 9:38 PM

https://youtu.be/hnAhveNy-8s

YouTubeSECourses

Wan 2.1 AI Video Model: Ultimate Step-by-Step Tutorial for Windows ...

Alibaba’s new Wan 2.1 text-to-video, video-to-video and image-to-video Open Source AI is unbelievable. In this tutorial I will show how you can install Wan 2.1 all publicly published models into your Windows PC with 1-click installation and use them with the easiest possible way. With the Gradio APP I have developed, you will be able to use Wan ...

masood•3/1/25, 9:39 PM

thanks

masood•3/1/25, 9:39 PM

does it wowk with text + image to video?

Furkan Gözükara SECoursesOP•3/1/25, 9:44 PM

new feaures

Mmasood does it wowk with text + image to video?

Furkan Gözükara SECoursesOP•3/1/25, 9:45 PM

yep

Furkan Gözükara SECoursesOP•3/1/25, 9:45 PM

it has video to video too

Furkan Gözükara SECoursesOP•3/1/25, 9:53 PM

with new update

Furkan Gözükara SECoursesOP•3/1/25, 9:53 PM

you can save video as 8fps and 4x interpolate and get 10 second 32 fps

Furkan Gözükara SECoursesOP•3/1/25, 9:53 PM

haha testing now

masood•3/1/25, 9:55 PM

that sounds so good. i think you have done quite good research on image generation, its time for videos now...and thanks for sharing all this research.

Mmasood that sounds so good. i think you have done quite good research on image generati...

Furkan Gözükara SECoursesOP•3/1/25, 9:55 PM

you are welcome

Furkan Gözükara SECoursesOP•3/1/25, 9:57 PM

10 seconds 30 fps

Furkan Gözükara SECoursesOP•3/1/25, 10:07 PM

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

Furkan Gözükara SECoursesOP•3/1/25, 10:07 PM

FFurkan Gözükara SECourses you can save video as 8fps and 4x interpolate and get 10 second 32 fps 😄

spirit18•3/1/25, 11:56 PM

Crazy

xlads•3/1/25, 11:59 PM

hey @Dr. Furkan Gözükara im trying to open up swarmui after a few months of not opening it and im getting this error any idea how i can fix it

FFurkan Gözükara SECourses Click to see attachment

Segundus•3/2/25, 12:23 AM

Sorry if obvious, is the WAN V12 app compatible with 5090 / Blackwell?

Zaulinator•3/2/25, 2:19 AM

Are we going to be able to use other wan models outside of what is in the download file?

humangirltotally•3/2/25, 4:36 AM

with the supir one click installer how come for batch processing, it ran out 3 images, now its eating up gpu/cpu because of llava and wont process the rest of them, 3 worked fine for some reason really quickly now its dragging.

SSegundus Sorry if obvious, is the WAN V12 app compatible with 5090 / Blackwell?

Furkan Gözükara SECoursesOP•3/2/25, 5:34 AM

yes it is compatiable

Furkan Gözükara SECoursesOP•3/2/25, 5:34 AM

sorry that i hadnt pushed update now pushed

Sspirit18 Crazy

Furkan Gözükara SECoursesOP•3/2/25, 5:34 AM

yep

Xxlads hey @Dr. Furkan Gözükara im trying to open up swarmui after a few months of not ...

Furkan Gözükara SECoursesOP•3/2/25, 5:34 AM

i dont know

ZZaulinator Are we going to be able to use other wan models outside of what is in the downlo...

Furkan Gözükara SECoursesOP•3/2/25, 5:35 AM

i plan to add lora support

Hhumangirltotally with the supir one click installer how come for batch processing, it ran out 3 i...

Furkan Gözükara SECoursesOP•3/2/25, 5:35 AM

weird

FFurkan Gözükara SECourses i plan to add lora support

Zaulinator•3/2/25, 5:37 AM

i just see merged wan models on civitai, so just curious if we would be able to use those

elieh•3/2/25, 8:56 AM

Is multi resolution training adviseable in Kohya? I see there's an "enable_buckets" setting - does it improve quality?

Karandeep Singh•3/2/25, 9:37 AM

Hi @Dr. Furkan Gözükara,
I noticed in the WAN 2.1 14B Image-to-Video 720P specifications - it shows "Number of Persistent Parameters In Dit (VRAM)" as 0 for 24GB cards. Is this correct, or possibly an error?
I'm asking because I'm observing my VRAM being fully utilized despite the parameter count showing as 0.

part.time.artist•3/2/25, 1:07 PM

I've scanned this thread but I am getting an error when running V23 of the model downloader:

Enter your choices (comma or dash separated, e.g., 1,3,5 or 1-3-5): 4
Created or verified directory: SwarmUI\Models
Created or verified directory: SwarmUI\Models\vae
Created or verified directory: SwarmUI\Models\diffusion_models
Created or verified directory: SwarmUI\Models\Stable-Diffusion
Created or verified directory: SwarmUI\Models\clip
Created or verified directory: SwarmUI\Models\yolov8
Created or verified directory: SwarmUI\Models\style_models
Created or verified directory: SwarmUI\Models\Lora
Created or verified directory: SwarmUI\Models\upscale_models
Traceback (most recent call last):
File "C:\Projects\SwarmUI\Download_Models.py", line 328, in <module>
download_models(selected_options)
File "C:\Projects\SwarmUI\Download_Models.py", line 66, in download_models
snapshot_download(
File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\huggingface_hub\utils_deprecation.py", line 101, in inner_f
return f(args, **kwargs)
File "C:\Users\john\AppData\Local\Programs\Python\Python310\lib\site-packages\huggingface_hub\utils_validators.py", line 124, in _inner_fn
return fn(args, **kwargs)
TypeError: snapshot_download() got an unexpected keyword argument 'local_dir'