Stable Diffusion guides

Seven short guides that answer the questions people ask most about Stable Diffusion, written by the team that runs the free tools on this site. Each one starts with the direct answer, then the details, then the tool where you can try it.

  1. What is Stable Diffusion?Stable Diffusion is an open-source text-to-image AI by Stability AI. What it does, how it works, the versions (1.5, SDXL, 3, 3.5) and how to use it free online.
  2. How to write a Stable Diffusion prompt?How to write a Stable Diffusion prompt: subject, style, light and quality in the right order, an annotated example, weights and the mistakes to avoid.
  3. What is a negative prompt?A negative prompt tells Stable Diffusion what to leave out: blur, deformed hands, watermarks, text. Ready-to-use lists, weights, and when it does nothing.
  4. What does the seed do in Stable Diffusion?The seed initialises the random noise Stable Diffusion starts from. Same seed and settings, same image: how to use it to reproduce, compare and refine results.
  5. What is a LoRA in Stable Diffusion?A LoRA is a small file that adds a style, a character or an object to Stable Diffusion without retraining it: how to use, weight and combine LoRAs.
  6. How to install Stable Diffusion locally?Hardware needed, Python and Git, the Automatic1111 web UI, SDXL or SD 1.5 model download, first launch and common errors. Free, offline and private.
  7. SDXL vs Stable Diffusion 3 vs SD 1.5: which one should you use?Stable Diffusion 1.5 vs SDXL 1.0 vs SD 3 / 3.5: resolution, VRAM, prompt understanding, text rendering, speed, licence, community models, and which one to pick.