Alie Jules Profile picture
May 12, 2023 15 tweets 8 min read Read on X
Prompt Cycling

This is one method I use to study prompts. (I totally made up the name for this technique)

The other two methods: Prompt Buildup and Prompt Stripping. (also made these names up, but they fit so well)

Thread + Prompts.

#midjourney #midjourneyv51 enigma, vector art --ar 16:9
The technique:
Keep one element constant while systematically changing another element to observe the effects on the output.

For this example of prompt cycling, I used:
Enigma - as the constant

Here's my starting point👉 Enigma

It's like a baseline. enigma
Then I start playing with the variable.

(and running out of my fast hours...😭)

So each prompt will be

Enigma, [variable] --ar 16:9

You can use any --ar = the aspect ratio for your image or leave it out for a square image.

16:9 (wide screen)

Digital ImageImage
You could use a variable that stays within particular parameters (style, aesthetic, etc.) or just go where your imagination takes you.

Enigma, techno noir --ar a16:9 ImageImage
I run each one at least two times because I'm aware of the possibility of remnants from previously unrelated images.

Enigma, futuristic --ar 16:9 (first run) ImageImage
Enigma, futuristic --ar 16:9

Second run. ImageImage
If, after the two runs, I'm not happy with what I'm getting, I move on. (some things just don't work well together)

Enigma, ancient Egypt --ar 16:9 ImageImage
If I like what I see, I can rerun the prompt many, many - many times! Like a lot, lot.

enigma, alien --ar 16:9 ImageImage
And I keep going.

While I do this, I'm just observing what I see.

Do I see:
Flying fish and birds, MJ likes to put into images?
Do I see clutter, distortion, artifacts, etc?
Do I see a person or landscape or something else?
And so on.
Observing - and storing it all for later. ImageImage
I know I'm not giving MJ a lot to work with.
More generic, less detailed prompts can give widely varying images.

I just observe.

I can tighten things up later if needed. This is really just for fun - although I'm using a somewhat scientific approach)

Enigma, clitch --ar 16:9 ImageImage
Observation 1.
Simply using "enigma" MJ most of the time interprets it as a female person.

So, for example, if I wanted to create a "male" enigma, I would have to specify it in my prompt.

Enigma, whimsical --ar 16:9 ImageImage
Observation 2.

MJ like to add fish, birds.. the usual - also into these ones, and if I didn't want that to happen, I probably would need to add more elements to the prompt.

Now, these things could also be because of the variable. ImageImage
Observation 3.

Most of the images are illustrations. Some of the styles are, of course, illustration types, but it's interesting to note that anyway.

So, if I wanted to get a photograph of Enigma. I would need to add "photo" or some other element to specify it as such. ImageImage
I'm certainly not this systematic all the time - not at all. But I find it helpful in figuring MJ out.

I'd love to see what you come up with!

Use:
Enigma [variable] --ar 16:9

Together we can learn so much more!

Enigma, photograph --ar 16:9 Image
I just realized I forgot to put the variable to this one. It's duotone.

• • •

Missing some Tweet in this thread? You can try to force a refresh
 

Keep Current with Alie Jules

Alie Jules Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @aliejules

May 18
Midjourney Style Reference (sref) explained

--sref codes are seeds - style reference seeds

Sref code allows you to replicate the style of that seed when you use the same --sref code with various prompts.

Why is this significant?
Using an sref makes is super easy to have a consistent style across any images.

It can be much more tedious and challenging to create this consistent style with prompting alone.

moreImage
There are 4.2+ billion srefs.

Sref seeds go from zero and up to 4294967295.

Explanation of why this top number here:


Many, many of these seeds are very similar, meaning we don't need to know/have them all.

Which is good because it would take me way, way, waaaaay, past my lifespan to go through them all. 😅
Srefs:

- Can't be combined together (possible in the future)

- Can't be used together with style you apply from an image - see screenshots

First screenshot
Add a style using the generated image (click 'style' at the bottom right).
Use the same prompt (click 'prompt' at the bottom right).
Generate the image grid.

Second screenshot
The generated image grid.

The sref 472 (in this case) as been removed and only the image style ref remains - if you look at the parameters on the right.

Not bad results, regardless!!Image
Image
Read 7 tweets
May 18
Place your subject/model in any setting - easy!

RenderNet has added a Character Lab to their suite of features making it super easy to create a character and then consistently place that character in any setting.

This is how. Image
1. Go to

2. Choose or create a character
- I chose Alice rendernet.ai/app
Image
3. Use an existing Canvas or create a new one
- I created a new one Image
Read 5 tweets
Apr 2
You can now edit your DALL·E images in ChatGPT

It's basically inpainting/generative fill.

This is how to do it 👇 Image
1. Click on your ChatGPT generated image to open the editor. Image
2. Click the icon to open the selection tool.

Once the tool is open you can adjust the size of the tool tip. Image
Read 10 tweets
Mar 17
tile parameter in Midjourney - Tutorial

Including prompts.
👇Image
When to use tile parameter?

When you want to create a seamless pattern.

Note. Using 'seamless pattern' in the prompt does not generated a 'true' seamless pattern. It may look like the pattern is seamless, but when lining up several images you'll notice that they do not create a seamless pattern.

Example:
Here I used 'seamless pattern' but not the tile parameter.

Prompt:
retro, yellow and orange, 70's patternImage
Image
How to use tile parameter

Add --tile at the end of your prompt

You can use --tile both on Discord and on Alpha Website.

Prompt:
retro abstract, circles and oval spears, lime green and aqua --tile --stylize 250Image
Image
Read 7 tweets
Oct 20, 2023
AI Image Upscaler Comparison

Paid and Free.

Let's compare.

Closeup of the original MJ image. Image
1) 2x Midjourney Upscaler Image
2) 2x with Photoshop Image
Read 13 tweets
Oct 11, 2023
Midjourney vs. Dalle-3 vs. Adobe Firefly

Same prompt for all.

10 spicy examples.

1. Image
2. Image
3. Image
Read 11 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us!

:(