L061 · How AI thinks · 2 min
AI that makes pictures
Image generators start from random noise and clean it up, step by step, until it matches the words you typed.
01 · The idea
Most image generators are diffusion models. During training they saw millions of pictures with captions, and they practised one odd skill: taking a picture covered in static and removing a little of the static at a time.
To make a new image, the model starts with pure static and removes noise over many steps, steering each step toward your prompt. A cat on a red sofa slowly appears out of the fuzz.
Results are often impressive, and they still slip. Small text, signs, the number of fingers, reflections and fine patterns are where mistakes usually hide. Two people in one scene can also blend together.
Specific prompts work best: say the subject, the setting, the style and the light. And when you share an AI image, say it is AI-made, especially if it shows real places or people.
02 · Think of it like this
It is like a sculptor who starts with a rough block of marble and chips away a little at a time. Your prompt tells them what is hidden inside the block.
03 · Do it now
04 · Quick check
Words in this lesson
See also
L117AI at work · 3 min
Copyright and AI images
AI images are easy to make and harder to own, so check the tool's terms and avoid copying real artists, brands or characters.
L296AI at work · 3 min
Restoring old family photos
AI can fix scratches, fading and blur in old photos, but it can also invent faces, so keep the original and label the new copy.
L297AI at work · 3 min
Making a picture from a description
An image generator draws from your words, so describing the subject, setting, style and mood clearly gets you much closer to what you pictured.
L059How AI thinks · 2 min
AI that makes video
Video generators turn a text description or a photo into a short moving clip, and the results are now realistic enough to fool people.