ok cool thanks!.. I think I might have gotten the inpainting thing to work now with my self trained
ok cool thanks!.. I think I might have gotten the inpainting thing to work now with my self trained model...
Fby the way you dont need special inpainting model to make this work 
Ayea I know.. but I am making really small characters and when fixing the face on something that's just a tiny part of the image a LOT of the times the head size get's wrong because I don't have any pictures where the face is such a small part of the image, then a proper inpainting models saves time because fewer of the seeds are unusable..
Fyou can also try img2img methodology
Flow denoise like 0.3
Fand 2x dimension
Fsame seed same prompt
Ayea also seems good..
Fdeepfloyd IF tutorial done
Ado you know if the open pose edior is broken?
AI get nothing when I use it..
Fhavent used recently
Iis this important for kohya ss lora training?
"A matching Triton is not available, some optimizations will not be enabled.
Error caught was: No module named 'triton'"
"A matching Triton is not available, some optimizations will not be enabled.
Error caught was: No module named 'triton'"
Fnope ignore
Ftriton not available on windows
Iah, thx
ZPlayed around with kandinsjy 2, it was ok. I still prefer auto1111
Fwhat you think about this thumbnail?
F,
ZGonna have to watch your video. Half the stuff i made in deep floyd was illegible
ZOr words were cut off
ZThumbnail looks great
Fthanks
Fhere another version
F
Fwhich one better
Fi am going to sleep hopefully see you tomorrow
Rhey I tried to update torch v2.0 in <venv>kohya_ss/scripts and got a weird error message even though I ran command in administrator mode:
RERROR: Could not install packages due to an OSError: [WinError 5] Access is denied: 'D:\kohya\kohya_ss\venv\Lib\site-packages\~umpy\.libs\libopenblas64__v0.3.21-gcc_10_3_0.dll'
Check the permissions.
Check the permissions.
RWARNING: Ignoring invalid distribution -illow (d:\kohya\kohya_ss\venv\lib\site-packages)
Ralso this one came up.
Rit worked fine for StableTuner (miniconda though) @Furkan Gözükara SECourses
HRecently I have some views, please let me know ,if is there any problems
H1.check unfreeze model will be better to help the model learning instance images datas, can also improve the generalization ability of the training model
H- When training design style model, class images are not necessary ,especially the instance images amount above 100.
H- Writing class name of class images ，leaving class images empty will also be helpful
H4.the function of class images is to help the model transfer learning
RSorted
H5.class name is to avoid pollution of the other class of the base model
H- If not well prepared, the class image can also mislead or pollute the training data
H@Furkan Gözükara SECourses
Adoes anybody know if the open pose editor extention is broken? When I make one and send to txt2img nothing happens, I jusdt get a dark screen.. using controlnet 1.1
Ai encounter this problem
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! (when
checking argument for argument mat2 in method wrapper_CUDA_mm)
how can i fix it
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! (when
checking argument for argument mat2 in method wrapper_CUDA_mm)
how can i fix it
Ai have rtx3050 and rtx 3080 in pc. my default gpu is rtx 3080
I have tried
I have tried
- reinstall
- install Python 3.10.9
- set cuda visible devices system 0,1
But problem is still.
Fi would try restart computer
Fclass images to prevent overtraining and keeping sanity of the model. if i dont use class images, and do some extensive training, when i type man i would see myself :d
Fcould be. they are still doing updates i think
Fcan you show your startup command line arguments?
Fhere example of mine
F
Vhey, is there any way to download a model from huggingface directly to google drive using colab?