Prompting image and media generators

Image generators turn a written description into a picture. They are useful for posters, college event banners, presentation visuals, YouTube thumbnails, app mock-ups and mood boards. The skill is the same one you learned for text: say exactly what you want. The difference is that you are describing something to see, so you need to name subject, style, light and framing.

In this tutorial you will build a prompt formula, make a poster for the Brew & Bean coffee shop, learn to refine results step by step and learn what these tools get wrong.

Prerequisites: access to any image generator. Several chat tools and design tools include free image generation with daily limits, and free access changes often, so check what your own tools offer today. The method works in all of them.

A short prompt such as "a coffee cup" leaves every decision to the tool, so you get a generic stock-style image. Add the decisions you care about, in roughly this order. Most tools weight the beginning of the prompt more, so put the most important thing first.

[Subject with details], [setting and time of day], [style], [camera angle and framing], [mood and colours]. Format: [aspect ratio or use, e.g. 16:9 thumbnail]. Leave empty space for [text/logo] at the [top/bottom].

What to expect: Write it as one or two flowing lines, not a long list. Try the same prompt three times: results vary each run, and that is normal.

Let us make a poster background for Brew & Bean's new cold brew. We start with a weak prompt and improve one part at a time, so you can see what each part changes.

A tall glass of cold brew coffee with ice cubes on a dark wooden cafe table, soft morning light from a window on the left. Photorealistic, shallow depth of field, calm and cosy mood, warm brown and cream colour palette. Portrait poster, 3:4, the glass in the lower third and a large empty area at the top for a title.

What to expect: Check: Is there empty space for text? Does the glass look natural (no extra handles, strange reflections)? Re-run if the glass or ice looks wrong.

Your first image is a draft. Many chat-based generators let you reply with changes ("same image, but make the background plain"). Others make you edit the prompt and run again. Either way, change one thing at a time so you know what caused the difference. Keep a note of prompts that worked.

A bold, high-contrast illustration for a thumbnail about [topic, e.g. learning Python in 30 days]: [main visual, e.g. a laptop with glowing code and a calendar]. Bright [colour 1] and [colour 2] colours, simple shapes, a clear focal point on the right, empty space on the left for large text. 16:9.

What to expect: Thumbnails are seen small, so check the image at thumbnail size. If it is hard to read at that size, simplify.

Simple flat vector logo concept for [business name], a [type of business]. Idea: [e.g. a coffee bean shaped like a cup]. Two colours only: [colour 1] and [colour 2]. Minimal, clean shapes, centred on a plain white background, no text.

What to expect: Use these as inspiration. AI logos often have fine details that do not scale, may resemble existing marks, and cannot always be edited as vectors. Have a designer or a vector tool redraw the one you pick.

A clean flat illustration for a presentation slide about [concept, e.g. how a request flows from a mobile app to a server and database]. Three simple icons connected by arrows, light background, [colour] accent, lots of white space, no text.

What to expect: Image generators are poor at accurate technical diagrams. Use this for decoration, and draw real diagrams in a diagramming tool.

I want to generate an image for [purpose]. My rough idea is: [your idea]. Write 3 detailed image prompts for it in different styles (photo, flat illustration, watercolour). Each prompt should name the subject, setting, style, composition, mood and colours, and say where to leave space for text. Keep each under 70 words.

What to expect: Paste each prompt into your generator and compare. This is a quick way to learn which style words work in your tool.

Other weak spots: counting ("exactly five cups"), hands and small objects, accurate maps and charts, real logos, and precise placement ("the cup on the left of the plate" is only sometimes obeyed). Cultural details can also be wrong: a request for a "South Indian breakfast" may mix dishes from different regions, so name the dishes you want.

For video and audio generators the same idea applies: describe subject, setting, style and camera or sound, but keep clips short and simple, because longer or complex scenes are more likely to go wrong. Features and limits change quickly, so read the tool's current guide.