omidsakhi/lorakit

Fast, config-driven SDXL LoRA & DreamBooth fine-tuning — train from a single YAML file. QLoRA + torch.compile.

3 best points · 0 comments · 1 Hacker News post · 19 GitHub stars · View on GitHub

Hacker News discussions

• Show HN: Streamlined SDXL Fine-Tuning for Rapid AI Model Iteration (3 points, 0 comments, by omidsakhi, 2024-09-29)