OneTrainer is a one-stop solution for all your stable diffusion training needs.

Prodigy and Schedule-Free, together at last.

optimizer & lr scheduler & loss function collections in PyTorch

Official Implementation of "ADOPT: Modified Adam Can Converge with Any β2 with the Optimal Rate"

A simple way to keep track of an Exponential Moving Average (EMA) version of your Pytorch model

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Convert every image file in a directory to JXL format

Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models

Stable Diffusion web UI

Lora beYond Conventional methods, Other Rank adaptation Implementations for Stable diffusion.

[ACL 2023] The official implementation of "CAME: Confidence-guided Adaptive Memory Optimization"