Back to Glossary
LoRALoRA
ローラ(ローラ)
AdvancedModels & Architecture
Low-Rank Adaptation — an efficient fine-tuning technique that adapts large models by training only a small number of additional parameters.
Why It Matters
LoRA makes fine-tuning affordable — you can customize billion-parameter models on a single consumer GPU.
Example in Practice
Fine-tuning Stable Diffusion with LoRA to generate images in a specific art style using just 20 training images.