eftSharptooth

Results 10 comments of eftSharptooth

[Feature Request] aarch64 build?

It should be possible, I used your setup to do it locally and it seems to be working fine. Its really just a convenience thing, and I believe supported by...

xformers on WSL2+Ubuntu for AUTOMATIC1111

whl file appears to work, I ran into the issue you just corrected with the mount condition check on the directories and manually added the whl install and that worked...

xformers on WSL2+Ubuntu for AUTOMATIC1111

I have a training running now, but once it is finished I will also test on a linux system running docker, as opposed to the previous successful Windows 10 test.

xformers on WSL2+Ubuntu for AUTOMATIC1111

The wheel does work on a linux host as well.

How do i fix this error?

This looks like a different error than the post you referenced, which had to do with non-ascii characters in filenames, metadata or captions/tags. This appears to be an issue with...

subprocess.CalledProcessError: Command '['E:\\kohya_ss\\venv\\Scripts\\python.exe', 'E:/kohya_ss/sd-scripts/flux_train_network.py', '--config_file', './test/output/config_lora-20240822-182849.toml']' returned non-zero exit status 3221225477.

It was my mistake earlier, no worries. Hey, I missed it earlier, but it says accelerator device is cpu. Could you open a terminal or command prompt and paste the...

subprocess.CalledProcessError: Command '['E:\\kohya_ss\\venv\\Scripts\\python.exe', 'E:/kohya_ss/sd-scripts/flux_train_network.py', '--config_file', './test/output/config_lora-20240822-182849.toml']' returned non-zero exit status 3221225477.

OK, so you will need to run an accelerate config in your venv. It would be good to also get your gpu info (single or multiple) and IDs if that...

subprocess.CalledProcessError: Command '['E:\\kohya_ss\\venv\\Scripts\\python.exe', 'E:/kohya_ss/sd-scripts/flux_train_network.py', '--config_file', './test/output/config_lora-20240822-182849.toml']' returned non-zero exit status 3221225477.

Im glad you are working! Happy training and good luck!

RuntimeError: Expected is_sm80 || is_sm90 to be true, but got false. (Could this error message be improved? If so, please report an enhancement request to PyTorch.)

This is a pytorch error, you most likely are using a 2080ti or lower GPU? It would also help to post the full log from the terminal window, as well...

OutOfMemory issue when starting FLUX1 Lora training

Lora type needs to be FLUX1