An image in 5 layers
Never use real personal data. If you need to, run it through the data cleaner.
Generate an image of [subject] in [place]. Style: [style]. Light: [light]. Framing: [shot], format [square / portrait / landscape]. No text, logos or recognisable people.
What result to expect
An image or description you can refine by changing one layer at a time.
Getting the most out of it
- Paste the prompt as is and only replace what is in [brackets].
- If the answer does not fit, do not start over: ask for “shorter”, “more formal” or “as a table”.
- Always review the result before using it: AI can get facts, dates or names wrong.
Before you paste it: quick checklist
- Describe style, light, framing and colours in short sentences.
- State the format: portrait, landscape or square.
- Don’t upload photos of other people without their permission.
- If the result isn’t right, change one element at a time.
How to adapt it to your assistant
The template works the same in ChatGPT, Gemini, Copilot or Claude because it only uses plain language. If your assistant supports fixed instructions (custom instructions, Gems or projects), you can store your preferred tone and format there and paste only the variable part. On a free plan, split long requests into two or three shorter messages.
More on this category
Templates for generating images and creative text by describing clearly what you want. The more specific the description (style, light, framing, colours), the easier it is to get it right first time. Respect image rights and don’t use other people’s photos without permission.