A highly memory-efficient layer-selective fine-tuning script for Stable Diffusion XL (SDXL) that trains only your chosen UNet layers while freezing the rest, allowing full-quality fine-tuning on just 12 GB VRAM.

A comprehensive toolkit for generating high-quality synthetic datasets using Meta's Llama Synthetic Data Kit. Supports PDFs, videos, documents & more for AI fine-tuning and testing.

This is a portal to these repositories from neutral aspect, as plainly a collection of texts and code to teach an AI.