ok, so the average speed is OK for my setup? ~4hrs and only 875/2800 on 12GB RTX3060
ok, so the average speed is OK for my setup? ~4hrs and only 875/2800 on 12GB RTX3060
F20 second / it is best
Fyou can get with 1024
Ftell me your step speed
S21 sec/it, avg loss 0.4
Fexcellent news we got for 16gb gpus
F
Fit is good
DI believe there were already 2 configs/ ranks (one slow & the other fast) for 16GB GPUs?
Swhere do I type my prompt to generate images? Or is Kohya_SS GUI doesn't support it?
Mthe learning rate in the flux config with single gpu is 0.00005. with sdxl it was 0.0004. is there a reason why it is much smaller? and does it mean we have to train it twice as much steps? so for example if i was training 4500 steps with sdxl do i have to train more than that because the learning rate is much smaller?
X"ERROR: Could not find a version that satisfies the requirement xformers==0.0.27.post2 (from versions: none)
ERROR: No matching distribution found for xformers==0.0.27.post2" Getting this error in very first step for "FLUX LoRA Training Simplified" I ran "pip install xformers" and it says that the xformers installed succsefully but when i try to install the first step again it says the same error
ERROR: No matching distribution found for xformers==0.0.27.post2" Getting this error in very first step for "FLUX LoRA Training Simplified" I ran "pip install xformers" and it says that the xformers installed succsefully but when i try to install the first step again it says the same error
TCan you do pip freeze in your venv?
TAnd post the result
XIm going to uninstall kohya_ss from my pc then reinstall now that i have necessary requirements hopefully it works
Xi uninstalled "kohya_ss from my pc" after getting this "ERROR: Could not find a version that satisfies the requirement xformers==0.0.27.post2 (from versions: none)
ERROR: No matching distribution found for xformers==0.0.27.post2
[notice] A new release of pip is available: 23.0.1 -> 24.2
[notice] To update, run: python.exe -m pip install --upgrade pip" installing xformers then reintalled it but still getting same error
ERROR: No matching distribution found for xformers==0.0.27.post2
[notice] A new release of pip is available: 23.0.1 -> 24.2
[notice] To update, run: python.exe -m pip install --upgrade pip" installing xformers then reintalled it but still getting same error
Sbro I had exact same problem and Gozukara replied it's fine
SMcan we use trained flux loras in kaggle?
X"To create a public link, set
ERROR: Exception in ASGI application
Traceback (most recent call last):
File "C:\Kohya_GUI_Flux_Installer_26 (1)\kohya_ss\venv\lib\site-packages\pydantic\type_adapter.py", line 279, in _init_core_attrs
self._core_schema = _getattr_no_parents(self._type, 'pydantic_core_schema')
File "C:\Kohya_GUI_Flux_Installer_26 (1)\kohya_ss\venv\lib\site-packages\pydantic\type_adapter.py", line 121, in _getattr_no_parents
raise AttributeError(attribute)
AttributeError: pydantic_core_schema
During handling of the above exception, another exception occurred:" getting this error when i click on the file inside of Kohya_ss configuration tab folder and the ui is also showing me "error
Connection errored out."
share=True in launch().ERROR: Exception in ASGI application
Traceback (most recent call last):
File "C:\Kohya_GUI_Flux_Installer_26 (1)\kohya_ss\venv\lib\site-packages\pydantic\type_adapter.py", line 279, in _init_core_attrs
self._core_schema = _getattr_no_parents(self._type, 'pydantic_core_schema')
File "C:\Kohya_GUI_Flux_Installer_26 (1)\kohya_ss\venv\lib\site-packages\pydantic\type_adapter.py", line 121, in _getattr_no_parents
raise AttributeError(attribute)
AttributeError: pydantic_core_schema
During handling of the above exception, another exception occurred:" getting this error when i click on the file inside of Kohya_ss configuration tab folder and the ui is also showing me "error
Connection errored out."
XAnyone know what it could be?
Fyes but they had lower quality
Fnow we can have best
Fyes each model different
Fstgep 2 fixes it
Fyes
Fyou can use
Fconnection error means internet related error
Fbu supir just got that error too
Fi suspect pydantic broken something
Frope pearl live now has face modification
![Dazzastrous [4090]](https://cdn.discordapp.com/avatars/871389071686135838/c4a5f4d81d9eeb18d856295d692e2c07.webp?size=40)
Dis it any faster interface ?
Dits painfully slow for me
![Dazzastrous [4090]](https://cdn.discordapp.com/avatars/871389071686135838/c4a5f4d81d9eeb18d856295d692e2c07.webp?size=16)
Fno interface slow :d
Dahhh
Dwhats that down to? bad programming?
Fi think python interface 
Dlol
Fonetrainer interface also sucks
Di think im gonna have to use a folder with less videos in it
Ftime to update configs
XStill getting connection error for kohya, will test rope pearl live for now 
XWild stuff lol
Fye
N@Dr. Furkan Gözükara DR there is a problem with Rope
before 3 days I used it, it was fine
but they did a recent update as I see based on the UI and the script isn't working
before 3 days I used it, it was fine
but they did a recent update as I see based on the UI and the script isn't working
Fsomething broken all
Nactually everything is working fine
but it doesn't detect the faces when you begin
it only detects the faces from the left box not the right box
but it doesn't detect the faces when you begin
it only detects the faces from the left box not the right box
Fgradio apps
Fi fixed errors of rope
Freinstall
Ndoes it have to do with onnx runtime?