AI Prompt Help

Try experimenting with different prompts. We recommend starting with 10-20 words with the most important aspects early in your text.

Subject
Start by stating the subject or content of the image. Describe what you want to see (e.g. a thin, tall bottle on a wooden table, short black bottle on a barrel)

Details and surroundings
What can you describe about where the subject is and what is around it? What perspective are you looking at the subject from (e.g. above, below, close-up)

What is the subject doing?
Standing there; lying down, being held, pouring out, moving...

What kind of feel or mood do you want to see?
Lighting (e.g. Studio Lighting), colours, emotion (e.g. sombre, vibrant)

Do you have a particular style in mind?
Name a specific style (e.g. gothic), Artist (e.g. Picasso), Media Type (e.g. watercolour)

  • Vivid details and concrete language usually produce more predictable results. Poetic or abstract wording can also produce surprising, but pleasing, results.
  • Keep your prompts concise and focus on one or two key elements, e.g. the main object and the setting.
  • Separate elements with commas
  • Include adjectives

Other tips

  • If your photos feel too abstract try adding "realistic"/"ultrarealistic" to your prompt.
  • Keep it Simple: it’s essential to keep your prompts straightforward. While adding detail and creativity is important, it’s also important not to overwhelm the AI with too much information.
  • Keep your prompts short and to the point, and focus on one or two key details you want to see in the image. This will help ensure the model can generate the image quickly and accurately.
  • For product shots, consider using the term: Studio lighting
  • Try including the word ‘bokeh’ to blur out the background

There are still plenty of limits to AI generation, so some types of image prompts are less likely to achieve the desired effect. A few things to avoid in descriptions are:

  • Complex scenes with multiple subjects
  • Detailed layout requests (for example, "A big red Object X on the left, friendly Object Y on the right, a small Object Z wearing Item A above them")
  • Requests for text (for example, a label saying 'Monkey Whisky'), because the AI generator doesn't know how to spell!

Even More Tips

Try these words and phrases for different art styles: "stencil art," "crayon," "chalk," "etching," "oil paintings," "ballpoint pen," "colored pencil," "Chinese watercolor," "pastels," "woodcut," "charcoal," "screen print," "photocollage," "storybook illustration," "newspaper cartoon," "vintage illustration from [decade]."

Other art styles to try: "surrealism," "Dadaism," "metaphysical painting," "orphism," "cubism," "suprematism," "De Stijl," "futurism," "expressionism," "realism," "Bauhaus," "color field painting," "impressionism," "baroque," "rococo," "mannerism," "ancient Egyptian papyrus," "ancient Roman mosaic."

Your description might include references to elements such as lighting, time of day, angle, and distance (for example, "close-up," "low camera angle") or technical elements such as camera type, lens, and so on. For example, a photo taken by a Canon DSLR, 35mm lens will look different from a flash photo from a disposable camera.

Other photography-related terms to play with: "trail cam," "CCTV," "VHS," "Polaroid," "infrared photography," "daguerreotype," "cyanotype," "photo from [a favorite magazine or website]," "film still from [a favorite movie or TV show]," "color splash," "extreme close-up," "wide-angle lens," "telephoto lens," "light leaks," "Lomography," "autochrome," "camera phone," "camera obscura," "warm lighting," "long exposure," "fast shutter speed," "back lighting," "low-key lighting," "golden hour," "blue hour," "macro lens," "motion blur," "shallow depth-of-field," "action photography," "candid portrait."