# Prompt Techniques And Idea Iteration (Hard)

If you’ve been experimenting with Midjourney for a while you probably noticed different styles of Midjourney [prompts](https://medium.com/generative-ai/how-to-launch-your-career-as-a-prompt-engineer-a-guide-for-creatives-bd1a1274276f): from comma-separated lists to long prose-like texts or prompts with carefully structured and labeled parts.

In this article, we will look at the most popular of these approaches and explore their strengths and weaknesses. We’ll cover:

* Additive prompting
* Category prompting
* Narrative prompting
* Interrogative prompting
* Single concept prompting
* Multi-Prompts / Prompt Weights
* Prompt Iteration

## Additive prompting <a href="#id-37ad" id="id-37ad"></a>

This is an approach similar to how we would interact with search engines: adding all the desired elements in a comma-separated list, although some may opt for pipes “|” or semicolons “;”. For a single prompt, it doesn’t matter which one you choose, but since Midjourney released its V5 model, I’ve tried to avoid commas whenever possible, as this makes things much easier if you want to use parts of your prompts with [Midjourney’s permutation feature](https://medium.com/design-bootcamp/complete-guide-to-midjourneys-permutation-feature-a2d8eb010c07) (more on that later).

**Pros:**

* Fast and intuitive
* Encourages shorter prompts

**Cons:**

* May become cluttered
* Determining semantic overlaps can be challenging in longer prompts

```
Cinematic Shot | Adventure | Mysterious | Explorers venturing into dense 
forest | Discovering hidden secrets and ancient relics | Forest location 
--ar 16:9 --v 5
```

<figure><img src="https://miro.medium.com/v2/resize:fit:700/1*4A7gnwj3OAVl5bWL6zYLNg.png" alt="" height="393" width="700"><figcaption><p>Image by author &#x26; Midjourney</p></figcaption></figure>

You can add as many elements as you like to steer Midjourney in the direction you want. However, you should follow a specific order as the prompts get longer: Things that come at the very end might lose effectiveness in long prompts. For example, [have a look at the Midjourney Cheat Sheet.](https://medium.com/design-bootcamp/the-midjourney-cheat-sheet-v5-54b5fd92d2da)

Additive prompting without considering prompt anatomy also leads to interesting results, especially with short prompts. However, it is less controllable.

```
Cinematic, adventure, mysterious, explorers, dense forest, hidden secrets, 
ancient relics, forest location, movie scene, eerie atmosphere, 
unknown discoveries --ar 16:9
```

<figure><img src="https://miro.medium.com/v2/resize:fit:700/1*1RYkgEC-vwxHVnbZO3s6kg.png" alt="" height="393" width="700"><figcaption><p>Image by author &#x26; Midjourney</p></figcaption></figure>

## Category Prompting <a href="#a27c" id="a27c"></a>

This approach also separates elements with commas, pipes, or semicolons but additionally adds a category name in front of groups of elements. The category names are not fixed, try to find what works best for you. Over time you will come up with sets of categories that fit your use case and style ([cinematic images](https://medium.com/design-bootcamp/mastering-midjourney-cinematic-prompts-over-the-shoulder-shots-486defe072e2), [product photography](https://medium.com/design-bootcamp/a-storytellers-guide-to-product-photography-with-midjourney-be96eab17cb7), [AI Art](https://medium.com/design-bootcamp/consistent-cinematography-with-midjourney-cinematic-prompt-cheatsheet-af1832800487), etc.)

**Pros:**

* clear and structured
* very well suited for automation with [ChatGPT](https://medium.com/generative-ai/mastering-chatgpt-five-advanced-prompt-techniques-you-should-consider-c0da587b74bf) (see below: Prompt-Iteration)
* easy to tweak, especially when it comes to multi-prompts (see below: Adding Weights: Multi-Prompts)

**Cons:**

* as with long prompts in general: you can lose control in the sense that you might overlook which phrase does what, or overload the prompt with things that no longer have any effect

Here’s the above prompt “translated” into a category prompting style:

```
IMAGE: Cinematic | GENRE: Adventure | MOOD: Mysterious | 
SCENE: A group of explorers venture into a dense forest, 
discovering hidden secrets and ancient relics | ACTORS: Explorers | 
LOCATION TYPE: Forest | TAGS: Adventure, mystery, forest, movie scene 
--ar 16:9 --v 5
```

<figure><img src="https://miro.medium.com/v2/resize:fit:700/1*w8hpO4BjXjuC9-AUQgiXyQ.png" alt="" height="393" width="700"><figcaption><p>Image by author &#x26; Midjourney</p></figcaption></figure>

Category prompting comes with an additional field for experimentation. The category names do have a subtle influence on the images. For example, here I used the same prompt to cycle through different names for the starting category (using **IMAGE, IMAGE\_TYPE, MEDIUM, VISUAL\_FORMAT)**. Thanks to the new [permutation feature](https://medium.com/design-bootcamp/complete-guide-to-midjourneys-permutation-feature-a2d8eb010c07), we can prompt for this in one go:

```
{IMAGE, IMAGE_TYPE, MEDIUM, VISUAL_FORMAT}: Cinematic | GENRE: Adventure | 
MOOD: Mysterious | SCENE: A group of explorers venture into a dense forest, 
discovering hidden secrets and ancient relics | ACTORS: Explorers | 
LOCATION TYPE: Forest | TAGS: Adventure, mystery, forest, movie scene 
--ar 16:9 --v 5 --seed 4000
```

<figure><img src="https://miro.medium.com/v2/resize:fit:2600/0*WKJ4SPmlo28tuy7S.png" alt="" height="1457" width="500"><figcaption></figcaption></figure>

<figure><img src="https://miro.medium.com/v2/resize:fit:2600/0*GreatZmXjqDK-q-T.png" alt="" height="1457" width="500"><figcaption><p>Image by author &#x26; Midjourney</p></figcaption></figure>

<figure><img src="https://miro.medium.com/v2/resize:fit:2600/0*hCwyZuyap--tfvGB.png" alt="" height="1457" width="500"><figcaption></figcaption></figure>

<figure><img src="https://miro.medium.com/v2/resize:fit:2600/0*-cDDkb9IzySVPMXJ.png" alt="" height="1457" width="500"><figcaption><p>Image by author &#x26; Midjourney</p></figcaption></figure>

Another technique that the category prompts help you with is flipping certain aspects of the original prompt. Of course, you can do this with any prompt, but the categories make it fairly easy to find the spots where you want to make changes. Here’s an example with the “IMAGE” category:

<pre><code><strong>IMAGE: Illustration | GENRE: Adventure | MOOD: Mysterious | 
</strong>SCENE: A group of explorers venture into a dense forest, 
discovering hidden secrets and ancient relics | ACTORS: Explorers | 
LOCATION TYPE: Forest | TAGS: Adventure, mystery, forest, movie scene 
--ar 16:9
</code></pre>

<figure><img src="https://miro.medium.com/v2/resize:fit:700/0*F9xcRrM__WxdSjw0.png" alt="" height="393" width="700"><figcaption><p>Image by author &#x26; Midjourney</p></figcaption></figure>

Here’s another one:

<pre><code><strong>IMAGE: copper engraving | GENRE: Adventure | MOOD: Mysterious | 
</strong>SCENE: A group of explorers venture into a dense forest, 
discovering hidden secrets and ancient relics | ACTORS: Explorers | 
LOCATION TYPE: Forest | TAGS: Adventure, mystery, forest, movie scene 
--ar 16:9 --v 5
</code></pre>

<figure><img src="https://miro.medium.com/v2/resize:fit:700/1*EmkQ9HDiwfYi1c4w6_1uKw.png" alt="" height="393" width="700"><figcaption><p>Image by author &#x26; Midjourney</p></figcaption></figure>

The third advantage of this type of prompt is that you can make them into multi-prompts quite easily. In multi-prompts, the parts of a prompt are separated by a double colon and accompanied by a number that indicates the relative importance of each part. This gives you more control over the prompt elements you want to emphasize. Here is an extreme example to illustrate this:

<pre><code>VISUAL_FORMAT: Cinematic::1 | GENRE: Adventure::1 | MOOD: Mysterious::1 | 
SCENE: A group of explorers venture into a dense forest, discovering hidden 
secrets and ancient relics::1 | ACTORS: Explorers::1 | 
<strong>LOCATION TYPE: Forest::10 | TAGS: Adventure, mystery, forest, 
</strong>movie scene::1 --ar 16:9 
</code></pre>

<figure><img src="https://miro.medium.com/v2/resize:fit:700/1*sgxASsNtbY7WsPJp6faVGw.png" alt="" height="393" width="700"><figcaption><p>Image by author &#x26; Midjourney</p></figcaption></figure>

## Narrative Prompting <a href="#dec0" id="dec0"></a>

This became more popular with V5 when Midjourney developers announced that the latest model would understand natural language better. Initially, this led some of us to start prompting entirely in prose [style](https://medium.com/design-bootcamp/mastering-midjourney-v5-part-2-the-stylize-parameter-8fd558aee4ce), which is actually not always the best idea.

But narrative prompting does have its advantages, especially when approaching a scene from its emotional side or when exploring new ideas or trying to find improvements for existing prompts.

**Pros:**

* great for exploration and experiments

**Cons:**

* harder to analyze and control

```
In a cinematic adventure scene, a group of explorers tread cautiously 
through a dense forest. With a mysterious atmosphere surrounding them, 
they uncover hidden secrets and ancient relics that lay hidden within the 
forest's depths. --ar 16:9 --v 5 
```

<figure><img src="https://miro.medium.com/v2/resize:fit:700/1*UCkXkwYbKverNd68gt4BlQ.png" alt="" height="393" width="700"><figcaption><p>Image by author &#x26; Midjourney</p></figcaption></figure>

## Interrogative Prompting <a href="#id-3761" id="id-3761"></a>

This is an underrated form of prompting steming from the days of V3 I would say. Shout outs to Eroteme Art who made this type of prompting an essential part of their artistic style.

**Pros:**

* great for exploration and experimentation
* can lead to [unexpected](https://medium.com/design-bootcamp/10-unusual-prompt-ideas-for-midjourney-you-probably-didnt-know-yet-a44ae00ecf84) and very artsy results

**Cons**

* unstructured, harder to control

Here’s the above translated into an interrogative approach:

```
What would a mysterious adventure scene look like, where a group of 
explorers venture into a dense forest and discover hidden secrets and 
ancient relics? --ar 16:9 --v 5 
```

<figure><img src="https://miro.medium.com/v2/resize:fit:700/1*3WrApcvGzrW3C_xIUI_MPQ.png" alt="" height="393" width="700"><figcaption><p>Image by author &#x26; Midjourney</p></figcaption></figure>

## Single Concept Prompting <a href="#id-81fa" id="id-81fa"></a>

This is a great approach for the initial exploration of themes, characters, and places that you can later start to combine into longer and more structured prompts. The core idea here is to only use a single concept and tweak it until you think it’s right.

For example from:

```
forest exploration --16:9
```

<figure><img src="https://miro.medium.com/v2/resize:fit:700/0*0B9-e-D4pLQiMnf_.png" alt="" height="393" width="700"><figcaption><p>Image by author &#x26; Midjourney</p></figcaption></figure>

To:

```
mysterious forest exploration --ar 16:9
```

<figure><img src="https://miro.medium.com/v2/resize:fit:700/0*OMWXcmsC4anH60c_.png" alt="" height="393" width="700"><figcaption><p>Image by author &#x26; Midjourney</p></figcaption></figure>

## Prompt Iteration <a href="#id-999e" id="id-999e"></a>

You can use Midjourne’s new permutation feature to cycle through different prompting techniques. Make sure you don’t use commas as structural separators, as they are part of Midjourne’s permutation syntax. Replace them with pipes “|” or semicolons “;”.

Here’s an example playing with the idea of “[alien](https://medium.com/predict/could-this-start-up-soon-be-contacting-aliens-using-dmt-542419385b4b) art”:

<pre><code>{
IMAGE_TYPE: Alien Art ; GENRE: Sci-Fi ; THEME: Extraterrestrial Culture ;
SCENE: An otherworldly masterpiece with vibrant colors; intricate details;
and an air of mystery ; LOCATION_TYPE: Alien World ; STYLE: Vibrant;
Intricate; Mysterious ; TAGS: Alien; Art; Masterpiece; Sci-Fi; Otherworldly;
Extraterrestrial; Culture; Vibrant Colors; Intricate Details; Mystery
<strong>--ar 16:9,
</strong>Alien; art; masterpiece; sci-fi; otherworldly; extraterrestrial; world;
<strong>culture; vibrant colors; intricate details; mystery --ar 16:9,
</strong>What would an art masterpiece look like if it didn't feature any alien or
otherworldly elements; focusing instead on a familiar terrestrial setting?
<strong>--ar 16:9,
</strong>In an extraordinary alien art masterpiece; the canvas comes to life with
vibrant colors and intricate details; unveiling the mysteries of an
<strong>otherworldly extraterrestrial world or culture. --ar 16:9,
</strong>Otherworldly alien masterpiece --ar 16:9
}
</code></pre>

After you confirmed this:

<figure><img src="https://miro.medium.com/v2/resize:fit:700/1*6XfVHtKs37UT4MzXSFI28Q.png" alt="" height="205" width="700"><figcaption></figcaption></figure>

You will get an overview of your prompting styles and how your idea gets interpreted with each of them:

<figure><img src="https://miro.medium.com/v2/resize:fit:2912/1*91_G3O9dSSk3SWgvBsKe1Q.png" alt="" height="1632" width="500"><figcaption></figcaption></figure>

<figure><img src="https://miro.medium.com/v2/resize:fit:2912/1*P8MnyoY6rlZEN0defrM0MQ.png" alt="" height="1632" width="500"><figcaption><p>Category and additive prompting</p></figcaption></figure>

<figure><img src="https://miro.medium.com/v2/resize:fit:2912/1*en5g1XPi9cXiv70xglzGjA.png" alt="" height="1632" width="334"><figcaption></figcaption></figure>

<figure><img src="https://miro.medium.com/v2/resize:fit:2912/1*6ySFynZj1gF0PFgJuX2-7A.png" alt="" height="1632" width="334"><figcaption></figcaption></figure>

<figure><img src="https://miro.medium.com/v2/resize:fit:2600/0*60IbC3XxEHJHa4QY.png" alt="" height="1457" width="334"><figcaption><p>Narrative, interrogative and single concept prompting</p></figcaption></figure>

Here’s another one:

<figure><img src="https://miro.medium.com/v2/resize:fit:2600/0*rqQQgS8J3iIFoNs4.png" alt="" height="1457" width="500"><figcaption></figcaption></figure>

<figure><img src="https://miro.medium.com/v2/resize:fit:2600/0*w7m4E-mkNKv04SCN.png" alt="" height="1457" width="500"><figcaption><p>Category and additive prompting</p></figcaption></figure>

<figure><img src="https://miro.medium.com/v2/resize:fit:2600/0*KoMFq_nNPiEXZtga.png" alt="" height="1457" width="334"><figcaption></figcaption></figure>

<figure><img src="https://miro.medium.com/v2/resize:fit:2600/0*9DhLwR_Cb2uZ7vs6.png" alt="" height="1457" width="334"><figcaption></figcaption></figure>

<figure><img src="https://miro.medium.com/v2/resize:fit:2600/0*lDhg_26AjStnYFW7.png" alt="" height="1457" width="334"><figcaption><p>Narrative, interrogative and single concept prompting</p></figcaption></figure>

Alright, since you’ve been paying close attention and reading until the end of this article, here’s a cool little bonus for you. :) Check out this ChatGPT prompt that gives you a ready-to-use permutation prompt to cycle through prompting styles. Have fun! 🚀

```
Here are different prompting styles that can be applied to prompt an AI image generator called Midjourney to produce images. Use them as reference. 

Category prompting: 
IMAGE: Cinematic | GENRE: Adventure | MOOD: Mysterious | SCENE: A group of explorers venture into a dense forest; discovering hidden secrets and ancient relics | ACTORS: Explorers | LOCATION TYPE: Forest | TAGS: Adventure; mystery; forest; movie scene --ar 16:9 

Additive prompting: 
Cinematic Shot | Adventure | Mysterious | Explorers venturing into dense forest | Discovering hidden secrets and ancient relics | Forest location --ar 16:9 

Interrogative prompting: What would a mysterious adventure scene look like; where a group of explorers venture into a dense forest and discover hidden secrets and ancient relics? --ar 16:9 

Narrative prompting: 
In a cinematic adventure scene; a group of explorers tread cautiously through a dense forest. With a mysterious atmosphere surrounding them; they uncover hidden secrets and ancient relics that lay hidden within the forest's depths. --ar 16:9 

Interrogative prompting:
What would a mysterious adventure scene look like; where a group of explorers venture into a dense forest and discover hidden secrets and ancient relics? --ar 16:9 

One concept prompting:
Mysterious forest adventure --ar 16:9

###

Be aware to not use commas inside the prompt! Commas are only allowed as separators between prompt styles! Even if this leads to wrong orthography: never use a comma inside a prompt!

For the topic X create all prompting styles. Be verbose, add whatever is needed to depict the image. Use this format :

{
[the category prompt],
[the additive prompt],
[the narrative prompt],
[the interrogative prompt],
[the one concept prompt]
}

Be aware to not use commas inside the prompt! Commas are only allowed as separators between prompt styles!
```


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://hoangs-organization-8.gitbook.io/midjourney-mastery/3.-deep-guide/prompt-techniques-and-idea-iteration-hard.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
