Cyeap
Cshow your cmd screen error , this ui error sir
TGitHub
When I try to use txt2image the first image is generated normally but when I try to generate the next one it shows "RuntimeError: CUDA out of memory. Tried to allocate 58.00 MiB (GPU 0; 4.00 G...
TSome solutions given there
Wit was multigpu error
Cı think you must change your settings or select your device
Wyes, that's what i did, sdxl was not able to figure out which gpu to use, i disabled my i9 integrated graphics
CIt's not a problem I've encountered before, but you can solve it like this. check out settings
Wand the error went away
Cor edit webui-user.bat
CAdd "SET CUDA_VISIBLE_DEVICES=1"
CGitHub
Is there an existing issue for this? I have searched the existing issues and checked the recent builds/commits What happened? In a dual-GPU Windows 10 system (2 x RTX-3090), only the first GPU is b...
Woh, wow thanks, that one is easier, i'll try that
Cvisit this
Bdoes anyone knows how to fix these errors?
Wthanks, man. this is exactly what i was looking for 
Wnot able to install / upgrade xformers now
TWhich version of CUDNN did you install? It wont work with CUDA 12 you have to use CUDA 11.8 versions
Wi think its a read issue. ugh what to do
BThank you, I'm using Torch 2.0.1+cu118
Z@Dr. Furkan Gözükara INstalling manually on my linux machine, where do we put the models at? I don't see a models folder for pixart?
Zhow many gigs of vram does pixart use? everytime i run app.py, it says out of vram
MI just trained with a very interesting set of images. Even though I selected the best photos, I could only find the best d_coef value for a quarter of them. I tried 0.85, it didn't come out strong. With 1.02 it was too strong, and even with 0.95. Finally, with 0.9 I managed to get a near perfect Lora. On another set of images, I managed to get one that turned out perfect the first time, even though there was nothing special about the photos. So there are still some exceptions where, even if the graph is good, you still need to polish the final result a bit.
Fi am following their repo
Fthey havent released yet
Fthat is very best PC
Fsurely enough
Fjust ignore them. tensorRT spits them out but works
Fyou set default cache folder
Fand they get downloaded into there
Fhugging face cache folder
Flook at the runpod instructions it shows
Fhow much vram you have?
Z12
Fcan you try low vram file
Fi added
SPerfect, thank you! Love your work
ZI will thank you
Fif you are on linux just look at the hyper parameter when starting the app.py
Flet me know result please
ZWill do
W@Dr. Furkan Gözükara i am on the 2nd episode of your course on udemy, have you in latter courses also specified how to prompt stable diffusion to generate amazing images like how people do (chubby:0.4) something like that
DI am training my photos for sdxl lora today. I used ohwx woman for my wife , can i use same ohwx man ? or ohwx should be different ?
Dok i am using bbuk man for me and ohwx woman for my wife
Dthis should help me to create photos of us nboth i think
DNeed clarity on sdxl Lora training kaggle notebook code
DThere is different run code for Lora training after koyass webui run
DIt's giving me old error
RHi, @Dr. Furkan Gözükara some questions about Kohya training for SD. I would like to train clothing based on a culture. Basically, using any checkpoint, I can just invoke them to wear the clothing with just a keyword. Would a Lora be the best option? Also, when training, how do you best caption the dataset so that the Lora does not remember the background, the face, color of the clothing, physical weight of the person, etc. I only want the clothing, and want to be able to determine the colors. How many images would be minimum for clothing? And what's the best way to caption? I have tried so many different ways, and haven't been very successful.
