Image generation prompt template: subject, style, light, composition

[SUBJECT: who or what, with 2-3 specific details], [ACTION OR POSE], in [SETTING: place, time of day, season, weather].

Style: [e.g. "documentary photograph", "watercolour illustration", "flat vector icon", "3D clay render"], inspired by [GENRE OR ERA, e.g. "1970s travel posters"].

Lighting: [e.g. "soft golden-hour backlight", "overcast diffused light", "neon rim light", "harsh midday sun"].

Camera and composition: [SHOT TYPE, e.g. "close-up", "wide establishing shot"], [ANGLE, e.g. "eye level", "low angle", "top-down"], [LENS FEEL, e.g. "35mm, shallow depth of field"], subject placed [e.g. "on the left third, empty space on the right for text"].

Colour palette: [2-4 colours or a mood, e.g. "muted teal and warm orange"].

Mood: [ONE OR TWO WORDS, e.g. "calm, hopeful"].

Avoid: [UNWANTED ELEMENTS, e.g. "text, logos, watermarks, extra fingers, clutter"].

Aspect ratio: [e.g. 16:9 for banners, 1:1 for social posts, 9:16 for stories, 2:3 for posters]

Example filled-in prompt:
An elderly beekeeper with a white veil and weathered hands, holding a honeycomb frame up to the light, in a wildflower meadow at sunrise in early summer.
Style: documentary photograph, inspired by 1970s National Park posters.
Lighting: soft golden-hour backlight with glowing edges.
Camera and composition: medium close-up, eye level, 85mm, shallow depth of field, subject on the left third, empty sky on the right for a headline.
Colour palette: honey gold, sage green, cream.
Mood: calm, warm.
Avoid: text, logos, watermarks.
Aspect ratio: 16:9

When to use it

Use this template whenever a short prompt such as “a beekeeper in a field” gives you random results. It is useful for blog headers, presentation slides, social media posts, mood boards and concept art, and for teams that want images in a consistent style across a project.

How to customize it

• [SUBJECT] is the most important line. Specific details (“weathered hands”, “white veil”) matter more than adjectives like “beautiful”.
• [ACTION OR POSE] and [SETTING] give the scene context and a story.
• Style sets the medium. Naming a genre or era is more reliable than vague words like “artistic”. Avoid naming living artists; many tools restrict it and it raises copyright and fairness concerns.
• Lighting has a large effect on mood and realism.
• Camera and composition controls framing. Asking for empty space is useful when you need room for a headline.
• Colour palette and Mood keep a series of images consistent.
• Avoid lists unwanted elements. In Midjourney use the --no parameter; in Stable Diffusion interfaces put these in the negative prompt field.
• Aspect ratio should match where the image will be used. In Midjourney add --ar 16:9; in other tools choose the size in the settings.

Why it works

Diffusion models generate an image from the description they are given, so anything you leave out is decided for you, often in a generic way. The template makes sure you specify the dimensions that most affect the result: content, style, light, framing and colour. Ordering the subject first helps because many tools give more weight to the beginning of the prompt.

Using the vocabulary of photography and illustration (“85mm”, “golden hour”, “top-down”) works well because image models learned from images described with those terms. For background, see our explainer on how diffusion models generate images.

Tips and variations

• Change one line at a time when refining, so you know what caused the difference.
• Some tools prefer short, comma-separated prompts; others, especially newer ones, follow full sentences better. Try both.
• Text inside images is still unreliable in many tools; add it later in a design app.
• For a consistent series, keep Style, Lighting, Palette and Mood fixed and vary only the subject.
• Check each tool’s terms on commercial use, and do not generate realistic images of real people without consent. Our guide on choosing an AI image generator compares the options.