Stable Diffusion

Stable Diffusion (by Stability AI) is the open standard for image generation. SD 3.5 (2025) improves prompt adherence and typography.

When to Use

• Control: You need exact composition control (ControlNet).
• Local Generation: Run on your own GPU. No censorship/cost.
• Fine-Tuning: training LoRAs on your own face/product.

Core Concepts

Diffusers Library

The Hugging Face library to run SD pipelines in Python.

LoRA (Low-Rank Adaptation)

Small adapter files (100MB) that add a style or character to the base model.