Software Engineering Courses (SECourses)•10mo ago

would the A6000 be faster than the l40?

ZZaulinator would the A6000 be faster than the l40?

Furkan Gözükara SECourses•2/27/25, 5:39 PM

ZaulinatorOP•2/27/25, 5:39 PM

i feel like my 4090 does the 1.3b model faster than the L40 lol

Furkan Gözükara SECourses•2/27/25, 5:40 PM

A6000 < L40 < L40S and so on

Furkan Gözükara SECourses•2/27/25, 5:40 PM

yes 4090 faster

Furkan Gözükara SECourses•2/27/25, 5:40 PM

5090 faster than L40S

Furkan Gözükara SECourses•2/27/25, 5:40 PM

because 1.3b model fits into vram

ZaulinatorOP•2/27/25, 5:40 PM

56 mins on the l40 to use the 1.4b model is crazy

ZZaulinator 56 mins on the l40 to use the 1.4b model is crazy

Furkan Gözükara SECourses•2/27/25, 5:43 PM

it is wrong

Furkan Gözükara SECourses•2/27/25, 5:43 PM

rtx 3090 takes 8 min

Furkan Gözükara SECourses•2/27/25, 5:43 PM

so something wrong i need to check later

FFurkan Gözükara SECourses so something wrong i need to check later 😄

ZaulinatorOP•2/27/25, 5:44 PM

ZZaulinator Click to see attachment

Furkan Gözükara SECourses•2/27/25, 5:44 PM

yep completey wrong

Furkan Gözükara SECourses•2/27/25, 5:44 PM

i can check back later i need to be afk now

FFurkan Gözükara SECourses i can check back later i need to be afk now

ZaulinatorOP•2/27/25, 5:45 PM

sounds good thank you

FFurkan Gözükara SECourses 1.3b could be best bet to train

HRK•2/27/25, 6:04 PM

I've just tried a lora I trained for 16 epoch with ~250 Images, the results are better than hunyuan no contest, it's very early in the training and yet it's sharp and looks quite good, i will share things when I get to a point where the training is perfect

HRK•2/27/25, 6:05 PM

while I would usualy train a bunch of videos first at res 512 then switch to images at res 1024, here only images at 704 and it's alright

uisato•2/27/25, 6:47 PM

Liminal Found Footage - [Flux Experiment]

More experiments, and project files, through: https://linktr.ee/uisato

https://www.youtube.com/shorts/dP3yCiqkHzA

ZaulinatorOP•2/27/25, 6:56 PM

yeah tried every combo of settings in MC with the l40, still like 10x slower for the 1.3b model than my 4090, so something is funky is going on.

V3ldrin•2/27/25, 9:00 PM

Hey, I was wondering why I get an "RuntimeError: CUDA error: out of memory" in kohya when using your "lora training best flux configs" with 16GB and less. (have a 24 GB card, and the 24 GB configs do work! ... )

FFurkan Gözükara SECourses compared to which gpu?

sergio_gonzo•2/27/25, 10:36 PM

compared to 4070 ti super

HHRK I've just tried a lora I trained for 16 epoch with ~250 Images, the results are ...

Furkan Gözükara SECourses•2/27/25, 10:38 PM

awesome

ZZaulinator yeah tried every combo of settings in MC with the l40, still like 10x slower for...

Furkan Gözükara SECourses•2/27/25, 10:39 PM

yes definitely wrong

Furkan Gözükara SECourses•2/27/25, 10:39 PM

i got to sleep though tomorrow morning has lecture :d

Ssergio_gonzo compared to 4070 ti super

Furkan Gözükara SECourses•2/27/25, 10:39 PM

let me check cuda counts

Ssergio_gonzo compared to 4070 ti super

Furkan Gözükara SECourses•2/27/25, 10:40 PM

5070 slightly better around 10%

Furkan Gözükara SECourses•2/27/25, 10:41 PM

sergio_gonzo•2/27/25, 10:41 PM

dr Furkan that is he 5070 super ti? tht is the want i though could work for me, in price

Ssergio_gonzo dr Furkan that is he 5070 super ti? tht is the want i though could work for me,...

Furkan Gözükara SECourses•2/27/25, 10:43 PM

i am not sure

Furkan Gözükara SECourses•2/27/25, 10:43 PM

if you can give me exact cuda numbers i can comment

Furkan Gözükara SECourses•2/27/25, 10:43 PM

but i recommend 4090 second hand if you can find

Furkan Gözükara SECourses•2/27/25, 10:43 PM

or even 3090 ti

Furkan Gözükara SECourses•2/27/25, 10:43 PM

more vram

Furkan Gözükara SECourses•2/27/25, 10:54 PM

video published

Furkan Gözükara SECourses•2/27/25, 10:54 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 ...

Furkan Gözükara SECourses•2/27/25, 10:55 PM

Writing Video chapters and manual fixing of Subtitles in progress

Furkan Gözükara SECourses•2/27/25, 10:55 PM

i got to go now

Furkan Gözükara SECourses•2/27/25, 11:10 PM

I plan to compare GGUF vs our APP tomorrow hopefully

ZaulinatorOP•2/28/25, 12:32 AM

whenever you get a chance Dr, let me know how to speed up the generation time in MC, thanks!

Original message was deleted

hamuz•2/28/25, 4:02 AM

opensource video models still have long way to go

hamuz•2/28/25, 4:02 AM

think about sd1.4 first release

hamuz•2/28/25, 4:02 AM

and we got sd1.5 fine-tunes in just a year

hamuz•2/28/25, 4:03 AM

quality improvements are just incredible between sd1.4 and sd1.5 fine-tunes

hamuz•2/28/25, 4:04 AM

we gonna see better, faster and local video models by end of 2025, im totally sure with that

AIGambino•2/28/25, 5:04 AM

This one I made is slightly better restoration, but not by much!

Taz•2/28/25, 9:44 AM

Found it on X. How true not sure, but need more investigation.

julius•2/28/25, 11:05 AM

Regarding upscaling in swarmui, what is the 4xrealwebphoto model that you use in tips-info @Dr. Furkan Gözükara ? Or which one is the best to use (for realistic portrait photos)

FFurkan Gözükara SECourses awesome

HRK•2/28/25, 2:37 PM

interestingly enough, training a ~250 image dataset on wan2.1 14b "only" takes 27gb gpu at res 1024 and rank 128, I wonder how far it can be pushed with a 80gb gpu

HRK•2/28/25, 2:38 PM

but to be fair it's quite slow per iteration (~23sec)

HRK•2/28/25, 2:39 PM

need to try videos next but I really want to push that training to the max

would the A6000 be faster than the l40?

Similar Threads