Glossary
Seed
A numerical value that initializes the random-number generator inside a model. Fixing the seed makes outputs reproducible — the same prompt + same seed yields the same output.
In depth
What it means in practice
AI image and video models include a random element in their generation process; the seed is what makes that randomness deterministic. Without specifying a seed, two runs of the same prompt produce different outputs. With the same seed, you get the same output.
Seeds are useful for two things: reproducing a result you want to share (give someone the prompt and the seed, they get your exact image), and iterating on a result you almost like (keep the seed, tweak one prompt word, see the difference). Most hilens models support seed control via an advanced parameter; the default seed is random per generation.
Related
Prompt
The text instruction given to an AI model that describes what to generate. For image and video models, prompts mix subject description, style direction, camera or composition hints, and optional negative prompts.
CFG scale
A parameter controlling how closely the model follows the text prompt. Higher CFG = more literal interpretation; lower CFG = more creative freedom. Typical range 4-12.
Inference steps
The number of iterative refinement passes the model takes to produce an output. More steps generally means higher quality, with diminishing returns above a model-specific threshold.