Software Engineering Courses (SECourses)•10mo ago

That's the first thing I tried. It does install with default setting but all custom steps are broken

That's the first thing I tried.
It does install with default setting but all custom steps are broken. Super weird. Done it million times, never had this issue

TTimson That's the first thing I tried. It does install with default setting but all cus...

Furkan Gözükara SECourses•3/2/25, 10:20 PM

weird

Furkan Gözükara SECourses•3/2/25, 10:20 PM

maybe you can report

Furkan Gözükara SECourses•3/2/25, 10:20 PM

https://discord.gg/2NjdmDwF

FFurkan Gözükara SECourses weird

sergio_gonzo•3/2/25, 10:33 PM

DrFurkan hi i hope everything id ok, do you have a APP that cna upscale video?

Ssergio_gonzo DrFurkan hi i hope everything id ok, do you have a APP that cna upscale video?

Furkan Gözükara SECourses•3/2/25, 10:33 PM

it is 1 thing i am researching

Furkan Gözükara SECourses•3/2/25, 10:33 PM

to both add into our wan app

Furkan Gözükara SECourses•3/2/25, 10:34 PM

and have seperate app

sergio_gonzo•3/2/25, 10:34 PM

thats would be awesome thanks

Ssergio_gonzo thats would be awesome thanks

Furkan Gözükara SECourses•3/2/25, 10:38 PM

yep

LMSO•3/2/25, 11:07 PM

Hi, does anyone know why I get this error after running swarmui on the GPU cloud? I'm not very knowledgeable about this, but I followed the steps in the tutorial and I get this error. The UI runs in the browser, but when I try to run a model, I see in the debug that it enters a loop saying 'ComfyUI-0 port 7821 waiting for server...'. 'Will attempt to load value set...'

LLMSO Hi, does anyone know why I get this error after running swarmui on the GPU cloud...

Furkan Gözükara SECourses•3/2/25, 11:11 PM

swarmui developer has to fix this

Furkan Gözükara SECourses•3/2/25, 11:11 PM

let me report

Furkan Gözükara SECourses•3/2/25, 11:12 PM

this is massed compute right? did you run update?

LMSO•3/2/25, 11:12 PM

Yes

LLMSO Yes

Furkan Gözükara SECourses•3/2/25, 11:13 PM

ok i reported error

Furkan Gözükara SECourses•3/2/25, 11:13 PM

this is because comfyui removed that package

LMSO•3/2/25, 11:14 PM

thanks! Is there any alternative for now to work around this?

LLMSO thanks! Is there any alternative for now to work around this?

Furkan Gözükara SECourses•3/2/25, 11:17 PM

dev said update should fix it

Furkan Gözükara SECourses•3/2/25, 11:17 PM

i am starting a new machine to test

Furkan Gözükara SECourses•3/2/25, 11:17 PM

if not auto fixed @NicB can make update on machine to fix

Furkan Gözükara SECourses•3/2/25, 11:18 PM

will tell you command to fix starting a new machine

LMSO•3/2/25, 11:19 PM

thx, I'll wait

LLMSO thx, I'll wait

Furkan Gözükara SECourses•3/2/25, 11:21 PM

you are welcome. machine getting initalized

FFurkan Gözükara SECourses you are welcome. machine getting initalized

AiInfluence•3/2/25, 11:29 PM

any news ?

AiInfluence•3/2/25, 11:29 PM

what version is the issue 0.9.5?

AAiInfluence any news ?

Furkan Gözükara SECourses•3/2/25, 11:31 PM

i am testing

AAiInfluence any news ?

Furkan Gözükara SECourses•3/2/25, 11:44 PM

it works

Furkan Gözükara SECourses•3/2/25, 11:44 PM

LMSO•3/2/25, 11:44 PM

I ran it again, and now it works

LLMSO thanks! Is there any alternative for now to work around this?

Furkan Gözükara SECourses•3/2/25, 11:44 PM

it works run this first

Furkan Gözükara SECourses•3/2/25, 11:44 PM

LLMSO I ran it again, and now it works

Furkan Gözükara SECourses•3/2/25, 11:44 PM

LMSO•3/2/25, 11:44 PM

Thanks

AiInfluence•3/3/25, 12:01 AM

Furkan Gözükara SECourses•3/3/25, 12:25 AM

i need to sleep hopefully see you tomorrow

LLMSO Hi, does anyone know why I get this error after running swarmui on the GPU cloud...

TimsonOP•3/3/25, 7:17 AM

It seems al existing installations of SwarmUI are broken by this update, needs clean install to reinstall backend and then it works

Pelolisu•3/3/25, 2:16 PM

MoD ControlNet Tile Upscaler for SDXL: Upscale Your Images with Ease!

Meet the MoD ControlNet Tile Upscaler for SDXL, a powerful tool that uses advanced technology to upscale your images without losing quality! Our app is designed to process images in tiles without leaving them blurry or with visible lines between the tiles. The result? Upscaled images with preserved details and smooth, natural transitions—all through a user-friendly interface.

What MoD Upscaler Offers:

Preserved Details: Unlike traditional upscalers, the MoD ControlNet Tile Upscaler enlarges your images while maintaining clarity and adding details that might otherwise be lost. Your photos gain more definition without sacrificing original quality.

Advanced Tiling Technology: We use a smart combination of techniques to ensure natural and smooth transitions between tiles. This means your upscaled images remain consistent and high-quality, even at higher resolutions. No more visible lines or imperfections!

Fast and Efficient: You don’t need a super-powered computer! Our app is optimized to run quickly and smoothly, even on simpler machines.

Easy-to-Use Interface: You don’t have to be an expert to use the MoD ControlNet Tile Upscaler. The interface is simple, intuitive, and designed so anyone can achieve professional-quality results without hassle.
Upscale your images without losing quality and with details preserved. Try the MoD ControlNet Tile Upscaler today!

Demo App: https://huggingface.co/spaces/elismasilva/mod-control-tile-upscaler-sdxl
Github Code: https://github.com/DEVAIEXP/mod-control-tile-upscaler-sdxl

MoD ControlNet Tile Upscaler SDXL - a Hugging Face Space by elismas...

GitHub

GitHub - DEVAIEXP/mod-control-tile-upscaler-sdxl: MoD Control Tile ...

MoD Control Tile Upscaler for SDXL Pipeline. Contribute to DEVAIEXP/mod-control-tile-upscaler-sdxl development by creating an account on GitHub.

dbx1969•3/3/25, 2:32 PM

Hey! Wanted to ask, I have recently trained both a Flux Finetune and LoRA sets following Furkans guides. My data set is about 500 high quality images of interior design featuring different rooms with various materials and furniture. I also have associated natural language captions that were generated with CGPT following instructions on how to describe the images.

The results for the finetune were very lackluster and the LoRA was a bit better, but still not as good as my old SDXL LoRAs in terms of geometric accuracies and textures.

Does anyone have any suggestions on what method I should best pursue? Is Flux the wrong model for this application? I am particularly drawn to its prompt adherence and I additionally intend to use control nets with it.

PPelolisu **MoD ControlNet Tile Upscaler for SDXL: Upscale Your Images with Ease!** 🚀 Me...

Furkan Gözükara SECourses•3/3/25, 3:21 PM

nice congrats

Ddbx1969 Hey! Wanted to ask, I have recently trained both a Flux Finetune and LoRA sets f...

Furkan Gözükara SECourses•3/3/25, 3:22 PM

if your dataset consistent no caption works better

Furkan Gözükara SECourses•3/3/25, 3:23 PM

also if you are trying to teach multiple similar concepts at once they bleed with flux

sergio_gonzo•3/3/25, 3:26 PM

DrFurkan i have this error i assume is for dont have the depencys of your escencial install cuda cudnn c++build tool,, it seems i dont have triton,, imust see your youtuibe video and instalal that