OneTrainer
OneTrainer copied to clipboard
Nerogar
OneTrainer is a one-stop solution for all your stable diffusion training needs.
# Description This pull request introduces the implementation of validation loss using FID (Fréchet Inception Distance) scores and provides comprehensive documentation for this feature (for the wiki). The implementation includes:...
### Describe your use-case. It would be really convenient to have the ability to drag a folder or folders you want to add to the concepts, into the window to...
### Describe your use-case. Read through [here](https://medium.com/@zhiwangshi28/why-flux-lora-so-hard-to-train-and-how-to-overcome-it-a0c70bc59eaf). Its a distilled model that allows better finetunes/loras. ### What would you like to see as a solution? support for this model ###...
- **Comment out non-functional alignprop steps.** - **Refactor out the traceback printing related to lint errors.**
### Describe your use-case. Sometimes I want to train a lora that will be used with other loras, and I want to see the results from sampling. So I don't...
Automatic saving is used to have multiple checkpoints after training, so you can choose the best one. However, you know in advance that the first x000 steps will not be...
### What happened? Caching is slower when continuing training from backup. ### What did you expect would happen? The caching speed would be the same as when i start a...
This shows up at every training: ``` src/diffusers/src/diffusers/loaders/single_file.py:348: FutureWarning: `original_config_file` is deprecated and will be removed in version 1.0.0. `original_config_file` argument is deprecated and will be removed in future versions.please...
I'm not sure whether we should put this information on the wiki, in README, or anywhere else. It can be pretty difficult to get the required CUDA Toolkit version on...
On every freshly cloned installation of OneTrainer (into a new, blank installation directory), `train_ui.py` triggers the following error on first launch: ``` Traceback (most recent call last): File "modules/ui/TopBar.py", line...