so instead fp16 using fp32 this will be much slower right? i have to test to see if there is a diffe
so instead fp16 using fp32 this will be much slower right? i have to test to see if there is a difference in the video
Fi tested fp16 weight vs fp32 weight
Fno difference
Fbut inference in fp32 i didnt test as it would require
Fastronomical vram 
SDr Furkan this model WAN could work in AMD gpus?
Fnope
Fi mean at least my code
Famd has to bring like 64 gb consumer gpus
Fthen community will make it work
Fbut for mere 24 gb no one gonna waste time
Jor anyone else knows how to fix this?
Sthe incremental in amount of vram remember me when intel only give us 4 cores in mainstrain,,, AMD must do somthing to change this
Jfound this in the docs. You can control the index apparently
JAlso seems like you can check the segmentation mask here https://github.com/mcmonkeyprojects/SwarmUI/issues/7#issuecomment-2187549309
GitHub
Hi, First, thank you for this awesome UI! I'm trying to generate an image, where all faces will be fixed, like in the ADetailer extension of A1111. Here is my prompt: oil painting of a male act...
Fyes i know
F<segment:yolo-face_yolov9c.pt-1,0.7,0.5> this inpaints first face
Fyou can sort faces now
F<segment:yolo-face_yolov9c.pt-2,0.7,0.5> second face
Jokay perfect, thanks!
JHope the baby is well btw 
Fthanks. he is good Alhamdulillah
Fi am about to fix numpy mismatch error message as well
Fimportant fix
DI read a comment saying Hunyan official img2vid is coming on the 6th. is that bullshit?
Fi think true we will see
Jthis also works now for controlling yolo-face, I didn't know that was possible
SDrFurkan hi, i have the WAN install v14,, i onley need to run window update or i need to do something more?
Fthis came recently
Fafter i requested so many months :d
Fdo a fresh install
Fmove model files
Fyou can also download newer models they are half size
Fsame quality
Jthat's awesome, I remember you saying you requested it in the tutorial video, but never thought anything happened about it
Jon massedcompute with cloudflare swarmui, are you guys also getting this sort of disconnection error sometimes? Can happen when I press "Generate", usually for 5-10 times in a row, and then it suddenly works again
Si could erase the folrder and donwload again the more optimized models?
Sthe new version has improve speed a bit?
Fdid you update and restart?
Fmachine could be broken
Fnot much yet but easier to load
Flesser space
Fsame quality
Fi am working on speed improvements
Sthank you for your hard work Dr Furkan
Fnmice
Fthey said fixed
FGitHub
Hello. I am trying to compile Flash Attention 3 and it fails I am able to compile Flash Attention 2 (venv) C:\a\d\hopper>python setup.py build_ext --parallel 8 bdist_wheel torch.version = 2....
Flet me try