gilga2024

I also noticed that at least on Linux there seem to be some memory leaks (both VRAM and RAM). Hence, my workaround is to close & reopen OneTrainer before starting...

I updated to the latest state on master-branch and can confirm that the problem still occurs, although behavior changed a bit. It now fails when saving the model instead of...

OS is Debian/Linux, VRAM is 12 GB and RAM is 32 GB (physical, a bit less in real). There are many *.json files, but no config.json in the whole directory...

Sorry, never used that button again after learning it does not export "everything" and implemented my own solution for that. Will do it after a current training run is complete...

Sorry for taking so long. But I had to finish some other stuff. Just recreated the problem using the attached config. The process was limited to a memory usage of...

One small update to this: I got it working (actually by accident) using fp16 instead of fp32 for the 'output data type' setting on the model tab. Maybe that helps...

I can only second this one. I have to use a folder consisting out of several thousand pictures for several trainings and therefor it has to be cached again and...

What I can add is that if you add a number of repeats >1 to your concept setting and enable crop/jitter you actually seem to get multiple versions of the...

I would still be interested in having this. Say you captioned image "backgrounds" (not the people behavior and appearance in it, but the setting they are in, landscape etc). Then...

Any news on this? Just read about the Flux branch and [checked it](https://github.com/Nerogar/OneTrainer/compare/flux), but found no other info. Any way one can help / provide input via testing?