What does the seed do in Stable Diffusion?

By Updated 2 min read

The seed is an integer that initialises the random noise every generation starts from. With the same seed, prompt, model and settings, Stable Diffusion produces exactly the same image; change the seed and you get a different composition for the same prompt. Setting it to -1 picks a random seed.

Why the seed matters

Diffusion starts from noise and every image is a deterministic function of that noise plus your settings. The seed is the recipe for the noise. That makes it the most useful tool for learning: fix the seed, change one thing, compare. It is exactly the method behind our artist style comparison: 1,731 artists, one seed, four fixed prompts, only the artist name changes, so the differences you see are the artist's effect and nothing else.

How to use it in practice

  1. Generate with seed -1 until a composition you like appears.
  2. Read the seed in the image info (Automatic1111 writes it in the PNG metadata and under the image) and paste it into the seed field.
  3. Now refine the prompt or the negative prompt word by word: the composition stays, the details move.
  4. When you change the sampler, the steps or the CFG, the same seed still gives a close image, which lets you compare settings fairly.

The prompt examples on this site list the seed with every image so you can start from a known result.

What breaks reproducibility

  • A different model or LoRA: the noise is the same but the denoiser is not, the image changes completely.
  • A different image size: the noise tensor has another shape, so the picture is unrelated even with the same seed.
  • A different GPU or software version: tiny floating-point differences can shift details; the composition usually survives.
  • SDXL and SD 3 add sub-seeds and noise offsets in some interfaces; leave them at their defaults for exact repeats.

Variations around a seed

Automatic1111 has a variation seed and a variation strength slider: at 0.1 to 0.3 you get siblings of the image, same pose and palette with small changes, useful to pick the best hands or face. An X/Y/Z plot with seeds on one axis and a prompt word on the other produces a comparison grid in one run.

Try it now, freeSee 1,731 artists rendered with one seed →

Questions people also ask

Is a bigger seed better?

No. The seed is a label for a noise pattern, not a quality setting; 7 and 4 294 967 295 are equally good. Only its repeatability matters.

Can I get the same image on another website with the same seed?

Only if the site uses the same model, size, sampler, steps, CFG and software. Between two Automatic1111 installations that is usually true; between different services almost never.

Why does the same seed give a different image on this site's tools?

The public tools resize your image to fit 1024 px and apply their own defaults, so the noise shape differs from your local setup. Inside the site, the same request with the same seed is reproducible.

All guides