Software Engineering Courses (SECourses)•13mo ago

sorry for delay here

Ffadounav @Dr. Furkan Gözükara Hello I can't paste the training files into the folder link...

Furkan Gözükara SECoursesOP•12/11/24, 12:26 PM

wont work for big files

Furkan Gözükara SECoursesOP•12/11/24, 12:27 PM

use notebook shared here : https://youtu.be/X5WVZ0NMaTg

YouTubeSECourses

How to Download (wget) Models from CivitAI & Hugging Face (HF) & up...

Notebook updated to V5 with huge improvements. If you are having trouble to download models onto your cloud platforms such as RunPod, Google Colab, Kaggle, Massed Compute or anywhere, this tutorial is made for you. Moreover, you can upload your files / models into your private Hugging Face repository and save them permanently privately and downl...

Furkan Gözükara SECoursesOP•12/11/24, 12:27 PM

it is also updated and now way faster better

Furkan Gözükara SECoursesOP•12/11/24, 12:30 PM

finally completed twitch streaming app it took me huge time

auto downloads and stream our videos from youtube : https://www.twitch.tv/secourses

Twitch

SECourses - Twitch

FLUX Tools Outpainting, Inpainting (Fill), Redux, Depth & Canny Ultimate Tutorial Guide with SwarmUI

mikemenders•12/11/24, 12:36 PM

When I realise that the easiest way was right under my nose all along... Priceless. I thought I'd start the Prodigy sampler without any extra parameters or normalization for 100 images with cosine, see what happens. The end result was a flexible, you could say perfect person-Lora for Pony. After that, I wondered why I had previously set all the extra parameters for Prodigy in the first place and why I hadn't trained without them before?

DDrocsid Imperator Maximus Oh, I know 😦 😦 😦

Kallamamran•12/11/24, 12:38 PM

Why SUPIR? I know it's good, but I'm not sure it's so good it's better than just using tiled upscaling with TT or SDUpscale and flux. For sure I don't think it's worth the disk waste/space...

KKallamamran Why SUPIR? I know it's good, but I'm not sure it's so good it's better than just...

Drocsid Imperator Maximus•12/11/24, 12:40 PM

As @Dr. Furkan Gözükara himself mentioned, SUPIRSUPIR is way, way, more faithful to the original texture than any model that came before it. A LoRALoRA just rebuilds what it thinks the texture looks like.

Drocsid Imperator Maximus•12/11/24, 12:41 PM

That's why I originally went through the trouble. However, I've since had to delete it 3/4 of the way through due to low disk space, heh.

Drocsid Imperator Maximus•12/11/24, 12:41 PM

There might be an alternative, but I don't know of one yet.

Drocsid Imperator Maximus•12/11/24, 12:42 PM

Not that JoyCaptionJoyCaption works either... (after another few GBs too)

fadounav•12/11/24, 1:09 PM

I can't find segmentation sort order @Dr. Furkan Gözükara

Capture_decran_2024-12-11_a_2.08.09_PM.png

DDrocsid Imperator Maximus As @Dr. Furkan Gözükara himself mentioned, `SUPIR` is way, way, more faithful to...

Kallamamran•12/11/24, 1:19 PM

SUPIR is just upscaling. It's not magic

Don't get me wrong. It's great... It just takes a shitload of resources though and it's not fast. SUPIR is like every other "upscaler" nowadays only a "upscaler with an upscaler" together with latent diffusion of the input image. Basically like img2img. "Good", sure, "that good"... Well... I don't think so. It still doesn't "know" anything. It's just guessing, so there's no guarantees the end result will be fantastic. If I can get fantastic results with SUPIR, using ~80GB of drive space and a very long time. I'd rather get fantastic results with ComfyUI TT or SDU in a fraction of the time using models I already have installed on my drive

KKallamamran SUPIR is just upscaling. It's not magic 😊 Don't get me wrong. It's great... It ...

Drocsid Imperator Maximus•12/11/24, 1:20 PM

So what's your recommendation then for 8GB VRAM lol?

Kallamamran•12/11/24, 1:20 PM

8GB VRAM and SUPIR doesn't marry that good either huh?

Kallamamran•12/11/24, 1:21 PM

That's quite limiting

Kallamamran•12/11/24, 1:21 PM

Hell I'm struggling with 16GB VRAM on my laptop right now and usually I find 24GB to be on the low end as well

KKallamamran SUPIR is just upscaling. It's not magic 😊 Don't get me wrong. It's great... It ...

fadounav•12/11/24, 1:26 PM

very interesting thank you for sharing your experience

KKallamamran 8GB VRAM and SUPIR doesn't marry that good either huh?

Drocsid Imperator Maximus•12/11/24, 1:28 PM

No, I mean another model entirely then with somewhat similar results, heh.

Drocsid Imperator Maximus•12/11/24, 1:29 PM

I just wasted 60+GB on a non-working SUPIRSUPIR and JoyCaptionJoyCaption

FFurkan Gözükara SECourses sorry for delay here

Drocsid Imperator Maximus•12/11/24, 1:52 PM

Thanks. Woah!

Drocsid Imperator Maximus•12/11/24, 1:52 PM

Is AuraSRAuraSR any better?

Drocsid Imperator Maximus•12/11/24, 1:52 PM

It appears to be faster... But I don't know how much space that one takes...

yassinemenace•12/11/24, 1:58 PM

@Dr. Furkan Gözükara When decreasing ddim and alpha should I increase learning rate 5e-5 for 128 what for example 64 ?

fadounav•12/11/24, 3:41 PM

@Dr. Furkan Gözükara I have 2 observations, I have the impression that the generation is long if I compare it to the one on openart in turbo mode. I took 2 A6000, btw, You said in your video that the comparison between lora and finetuning is like night and day. I wanted to know at what level, because if it's rendering quality, I think it's pretty similar. the first image is made with openart and the second with finetuning , it's even worse in finetuning because I've lost the comic illustration aspect.

fadounav•12/11/24, 3:56 PM

1521-illustration_style_of_an_fnfn_man_short-modelTest1-1549214662.jpg

fadounav•12/11/24, 5:17 PM

for info I was able to recover the comic illustration style by adding negative prompts, photorealistic, hyper-realistic, realistic details, etc.

fadounav•12/11/24, 5:25 PM

I think there's only one GPU working, whether it's for one image or 10 in a generation. is that normal? @Dr. Furkan Gözükara

Capture_decran_2024-12-11_a_6.24.26_PM.png

Drocsid Imperator Maximus•12/11/24, 5:54 PM

@Dr. Furkan Gözükara Any reliable way to convert .pt.pt .pth.pth .bin.bin into .safetensors.safetensors?

Drocsid Imperator Maximus•12/11/24, 5:57 PM

I have been testing this, which didn't work correctly, sadly.

GitHub

GitHub - MackinationsAi/convert-2-safetensors: A simple repo for si...

A simple repo for single or batch converting .pt, .pth & .bin models into .safetensors models. - MackinationsAi/convert-2-safetensors

Drocsid Imperator Maximus•12/11/24, 6:01 PM

This one now works for some models, but still not all.

GitHub

GitHub - jtabox/safetensors-converter: Converts pth/pt files to saf...

Converts pth/pt files to safetensors. Contribute to jtabox/safetensors-converter development by creating an account on GitHub.

Drocsid Imperator Maximus•12/11/24, 6:48 PM

Anybody familiar with this error? Happens with both .pth.pth and .safetensors.safetensors files.

Drocsid Imperator Maximus•12/11/24, 6:56 PM

@Dr. Furkan Gözükara Any idea on how to resolve this error?

Drocsid Imperator Maximus•12/11/24, 6:58 PM

FYI, useful repo listing all SOTA upscalers sorted by year of release.

GitHub

GitHub - ChaofWang/Awesome-Super-Resolution: Collect super-resoluti...

Collect super-resolution related papers, data, repositories - ChaofWang/Awesome-Super-Resolution

Ffadounav I can't find segmentation sort order @Dr. Furkan Gözükara

Furkan Gözükara SECoursesOP•12/11/24, 8:14 PM

it is never added

Furkan Gözükara SECoursesOP•12/11/24, 8:14 PM

please leave a reply here

Furkan Gözükara SECoursesOP•12/11/24, 8:14 PM

https://github.com/mcmonkeyprojects/SwarmUI/pull/289

GitHub

Add Segmentation Ordering for Yolo segmentation by aimerib · Pull R...

Allow yolo segmentation to sort by left-right, top-bottom, largest-smallest, and reverse that order.
Params added to Regional Segmentation Group

Yyassinemenace @Dr. Furkan Gözükara When decreasing ddim and alpha should I increase learning r...

Furkan Gözükara SECoursesOP•12/11/24, 8:15 PM

dont change alpha and learning rate

Ffadounav @Dr. Furkan Gözükara I have 2 observations, I have the impression that the gener...

Furkan Gözükara SECoursesOP•12/11/24, 8:16 PM

what do you mean by openart?

Ffadounav I think there's only one GPU working, whether it's for one image or 10 in a gene...

Furkan Gözükara SECoursesOP•12/11/24, 8:17 PM

you need to manually add backend

Furkan Gözükara SECoursesOP•12/11/24, 8:17 PM

shown in many tutorials by now

DDrocsid Imperator Maximus @Dr. Furkan Gözükara Any reliable way to convert `.pt` `.pth` `.bin` into `.safe...

Furkan Gözükara SECoursesOP•12/11/24, 8:17 PM

not that i know

DDrocsid Imperator Maximus I just wasted 60+GB on a non-working `SUPIR` and `JoyCaption`

Kallamamran•12/11/24, 8:17 PM

Oh it's working. You must have done something wrong installing

DDrocsid Imperator Maximus @Dr. Furkan Gözükara Any idea on how to resolve this error?

Furkan Gözükara SECoursesOP•12/11/24, 8:17 PM

you should ask the source - i dont know atm

fadounav•12/11/24, 8:20 PM

@Dr. Furkan Gözükara openart is a platform on which I used to create my images before they changed their prices. I used to make fairly high-quality lora flux, after a few image generations on Swarmui I find the quality very good, little waste, but it's a bit slow, I'm going to test with an L40 to go faster what do you think? would it be better with 2A6000?

Ffadounav @Dr. Furkan Gözükara openart is a platform on which I used to create my images ...

Furkan Gözükara SECoursesOP•12/11/24, 8:21 PM

for lora

Furkan Gözükara SECoursesOP•12/11/24, 8:21 PM

you can train 2x gpu

Furkan Gözükara SECoursesOP•12/11/24, 8:21 PM

so yes almost 2x spee

Furkan Gözükara SECoursesOP•12/11/24, 8:22 PM

for fine tuning you cant you need 80 gb gpus

DDrocsid Imperator Maximus No, I mean another model entirely then with somewhat similar results, heh.

Kallamamran•12/11/24, 8:22 PM

Maybe you could get away with a quantized model of Flux, but I really coudn't say. I've tried Q5 and that gives rather good results. I'm not sure if it can be run with 8-steps lora though, so maybe there is no time savings either with that.

FFurkan Gözükara SECourses you can train 2x gpu

Kallamamran•12/11/24, 8:23 PM

https://tenor.com/view/powerful-iron-mask-electricity-shock-zap-gif-18641022

Tenor

sorry for delay here

Similar Threads

Similar Threads

Similar Threads