Skip to content
Learn Motion
ExploreHow it worksMembership
Log in
Learn Motion

How Generative AI Creates Text, Images, and Videos from a Prompt

1The Shared Idea Behind All Generative AI2How a Prompt Becomes an Instruction3Generating Text: One Token at a Time4Generating Images: From Noise to Picture5Generating Video: Adding Time6Comparing the Three Modalities and Judging Outputs
Generating Text: One Token at a Time

One Dial Between Boring and Wild

2 / 4
Set the randomness slider low first and run the loop several times. The tallest bar keeps winning, so the runs come out nearly identical, and the text starts to feel flat. Now push the slider high and run again. The bars level out, unlikely tokens get picked, and the runs diverge from one another. That divergence is the whole point: the model's raw output is a spread of possibilities, and the slider decides how adventurous the pick is. Neither end is correct. Low settings are for answers you need to reproduce; high settings are for exploring options you intend to judge yourself.
0:00 / 0:00

The model's output at each step is not a single token but a probability distribution over many candidates. A sampling rule then chooses one. If the rule always takes the highest-probability token, the text becomes predictable and repetitive; if it sometimes takes lower-probability tokens, the text becomes varied and surprising, and occasionally incoherent.

This trade-off is usually exposed as a single adjustable setting, often called temperature. Low temperature concentrates the choice on the most likely tokens, which suits tasks needing stable, repeatable answers such as extracting a date or following a strict format. High temperature flattens the distribution so unlikely tokens get a real chance, which suits brainstorming, naming, and creative variation. The same prompt run twice at high temperature can produce noticeably different answers; at very low temperature the runs converge on nearly the same text.

Previous2 / 4Next

Learn Motion

Generate a course. Learn it properly.

Operated by Wuhan Daoyin Technology Co., Ltd.

Contact: [email protected]
Privacy PolicyTerms of Service

© 2026 Learn Motion