---
title: "What Makes a Good AI Image Prompt? | ImageQuarry"
url: https://www.imagequarry.com/faq/what-makes-a-good-ai-image-prompt/
last_updated: 2026-10-20
---

# What makes a good AI image prompt?

A good prompt describes the scene in full sentences: the subject, the setting, the light, the camera view and what the image is for. Google's guidance for its image models says that more detail gives you more control and that explaining the purpose helps the model.

Say what you want rather than what you don't. Google's example: instead of "no cars", write "an empty, deserted street with no signs of traffic".

For a busy scene, split the request into steps: the background first, then the main subject, then the details, as Google's guidance recommends.

Expect to refine. The first image shows what the model understood, and the next instruction corrects what it missed.

In ImageQuarry the refining happens in the same conversation: you ask for a change to the version you chose, and the earlier version is kept.

_Source: Google's Gemini image generation best practices; checked October 20, 2026._

Next step: [All questions](https://www.imagequarry.com/faq/)

## Related questions

- [Should I describe the camera and lens in an image prompt?](https://www.imagequarry.com/faq/should-i-describe-camera-and-lens-in-a-prompt/): Yes, when the framing matters.
- [What is a negative prompt?](https://www.imagequarry.com/faq/what-is-a-negative-prompt/): A list of what you do not want; describe the scene instead.
- [Why doesn't the AI image follow my prompt?](https://www.imagequarry.com/faq/why-does-ai-not-follow-my-prompt/): Vague, conflicting or negative wording, or a model limit.
- [How specific should an edit instruction be?](https://www.imagequarry.com/faq/how-specific-should-an-edit-instruction-be/): Name the change, where it happens and what stays.

Last reviewed 2026-10-20 by ImageQuarry.

## Put a good prompt to work

Describe the subject, setting, light and purpose, then refine the result in the same conversation.

