you are installing with sdxl download, can you go to custom setting step?
you are installing with sdxl download, can you go to custom setting step?
Fok pay attention to cmd
Fyou will see it
Fthis is custom settings actually :d
Fi picked sdxl willingly to test
Fye no issues it installed
Fmaybe your browser not showing
Frestart it
TI tried clean install couple of times, no luck
Ftry private window
TThat'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
It does install with default setting but all custom steps are broken. Super weird. Done it million times, never had this issue
Fmaybe you can report
F
SDrFurkan hi i hope everything id ok, do you have a APP that cna upscale video?
Fit is 1 thing i am researching
Fto both add into our wan app
Fand have seperate app
Sthats would be awesome thanks
Fyep
LHi, 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...'
Fswarmui developer has to fix this
Flet me report
Fthis is massed compute right? did you run update?
LYes
Fok i reported error
Fthis is because comfyui removed that package
Lthanks! Is there any alternative for now to work around this?
Fdev said update should fix it
Fi am starting a new machine to test
Fif not auto fixed @NicB can make update on machine to fix
Fwill tell you command to fix starting a new machine
Lthx, I'll wait
Fyou are welcome. machine getting initalized
Aany news ?
Awhat version is the issue 0.9.5?
Fi am testing
Fit works
F
LI ran it again, and now it works
Fit works run this first
F
F
LThanks 
A
Fi need to sleep hopefully see you tomorrow
TIt seems al existing installations of SwarmUI are broken by this update, needs clean install to reinstall backend and then it works
PMoD 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
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
GitHub
MoD Control Tile Upscaler for SDXL Pipeline. Contribute to DEVAIEXP/mod-control-tile-upscaler-sdxl development by creating an account on GitHub.
DHey! 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.
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.
Fnice congrats
Fif your dataset consistent no caption works better