A highly memory-efficient fine-tuning toolkit for SDXL and ANIMA, combining modern VRAM-saving techniques with custom optimizers to enable full-quality model training on GPUs with as little as 12 GB of VRAM.

Automates the setup and installation of invoke-training on Windows, Mac, and Linux.

Enhanced Prodigy optimizer with ~21% GPU speedup, independent D estimation for multi-component models, and improved stability. Drop-in replacement for Prodigy with same API.