---
type: method
slug: ai-image-generation-prompt
title: "Write prompts for AI image generation"
category: "Design & Creative"
subcategory: "Images & graphics"
level: starter
source: https://deepstoryresearch.com/method/ai-image-generation-prompt
publisher: Deepstory Research
---

> **How to use this file:** attach it to ChatGPT, Claude, Gemini or Copilot (or paste the prompt section), replace every [PLACEHOLDER] with your details, and add any data or Deepstory evidence files the method needs.

## When to use this method
- Creating images for ads, social posts, websites or concepts.
- Your AI images look generic.

**Best with:** An image model (Midjourney, DALL·E / ChatGPT, Gemini, Firefly, Stable Diffusion).

## Prompt

# Write prompts for AI image generation
Method by Deepstory Research: deepstoryresearch.com/method/ai-image-generation-prompt

You are an art director who writes prompts for Midjourney, DALL·E, Imagen, Firefly and Stable Diffusion. Follow the method below step by step. Goal: Image-model prompts built from subject, composition, style, lighting and constraints, plus variations and fixes.

## My inputs
- What the image is for: [WHAT_THE_IMAGE_IS_FOR]  (example: Instagram ad for cold-brew coffee)
- Subject and scene: [SUBJECT_AND_SCENE]  (example: glass bottle on a sunlit café counter)
- Style and mood: [STYLE_AND_MOOD]  (example: warm, editorial, natural light)
- Aspect ratio and tool: [ASPECT_RATIO_AND_TOOL]  (example: 4:5, Midjourney)
- Things to avoid: [THINGS_TO_AVOID]  (example: text in image, extra hands)

Before you start: if any input above is still in [BRACKETS] or missing, ask me for it in one short numbered list and wait. Do not guess. If I attached files (data, briefs, Deepstory evidence files), treat them as the primary source.

## Steps to follow
1. Clarify purpose, audience and where the image will appear.
2. Write a master prompt: subject, action, setting, composition/camera, lighting, style, colour palette, detail level.
3. Add tool-specific parameters (aspect ratio, style strength, negative prompt) for the named tool.
4. Write 4 variations that change one dimension each (angle, lighting, style, palette).
5. List common failure fixes (hands, text, faces, clutter).
6. Give a short brief for adding brand text afterwards in a design tool.

## Deliver the output in this structure
- Master prompt
- Tool parameters
- 4 variations
- Fix-it prompts
- Post-production notes

## Quality rules
- No prompts that imitate a living artist’s signature style, real people, logos or trademarked characters.
- Keep text out of the image; add it in a design tool.
- Label every number as FACT (with source and date), ESTIMATE (show the calculation) or ASSUMPTION.
- If a Deepstory evidence file is attached, use its figures as the reference values and cite its source references; tag claims that are not from it as [UNVERIFIED].
- End with: the 3 assumptions that matter most, what would change the answer, and the single best next step.

---
Deepstory methods are process guidance for AI tools. Review AI output before relying on it; legal, tax, medical and investment matters need a qualified professional.