OneTrainer
OneTrainer copied to clipboard
Nerogar
OneTrainer is a one-stop solution for all your stable diffusion training needs.
### Describe your use-case. in the backup tab there's "backup now" I've tried converting a backup to a Lora but it fails, it doesn't say why. it just says could...
### Describe your use-case. In the tools tab there's dataset tools, convert model tools, sampling tools, profiling tools. On a small monitor the Dataset tool window is off the screen...
### What happened?  train device cuda:1 does not work. train device cuda:0 works. train device cuda works. Simple solution (crutch): In start-ui.bat add set CUDA_VISIBLE_DEVICES=1  ### What did...
 
I'm getting an error each time I try to run the training process. For context, I'm using Windows 11 with an RTX 3090, and both A111 and ComfyUI work fine...
### Describe your use-case. SDXL Lightning is a new and extremely fast version of SDXL. It would be great if we could fine-tune SDXL Lightning models. https://huggingface.co/ByteDance/SDXL-Lightning ### What would...
### Describe your use-case. Right now, caching appears to be all or nothing, if you change the source dataset(s) you are forced to recache the entire concept otherwise it will...
Currently, ZLUDA installer of OneTrainer that I previously implemented is buggy as it depends on `PATH` env var and needs to patch torch with dll files from ZLUDA. The new...
### What happened? I had OneTrainer working fine before on the same machine I just pulled latest changes [here](https://github.com/Nerogar/OneTrainer/commits/master/) and updated dependencies with `update.sh` After update I started getting this...
### Describe your use-case. As a new user, it looks like there is a single config, and everything is unified. This is because there is a single, top level "config"...
