Alie Jules Profile picture
May 13, 2023 β€’ 13 tweets β€’ 7 min read β€’ Read on X
Working a Prompt - Midjourney

The promised process of how to generate images like this πŸ‘‡πŸ‘‡πŸ‘‡

Note!
This is not the only way or the right way - just simply one way I work and play with a prompt to achieve an aesthetic and to observe results. Image
1. Prompt elements

Constants: Extreme close-up, photo, red hair, beautiful girl (a woman would work too)

I don't add "freckles" - MJ will add freckles when you prompt red hair.

If you add "freckles" you can get something like this: Super freckles. Image
I add "photo" to make sure the created images are photos. i.e. I'm directing MJ to generate a photograph.

If I don't use "photo" I can sometimes get a not-so-realistic photo image (top right).

prompt:
extreme close-up of a beautiful redheaded girl Image
I'm starting with the default version v5.1 - I don't need to add that to the prompt.

I'm not adding any aspect ratio parameter, so MJ outputs a square image.

This is the starting configuration.

Prompt:
extreme close-up photo of a beautiful redheaded girl Image
This is already pretty amazing! You could stop here if you are happy with the results.

Just do some reruns and pick your favorites.

But we are going to keep going.

What happens if I do this:
extreme close-up photo of a beautiful girl with red hair Image
Do you notice any differences?

Subtle, maybe.

Let's add in aspect ratios.

Because I'm not sure yet, which one I prefer, "redheaded" (left) or "with red hair" (right), I'm going to run both.

extreme close-up photo of a beautiful girl with red hair --ar 2:3 ImageImage
At this point, you may notice artifacts on some of the images. The little water droplets or "bumbles," haha - not sure what to call them.

Like in this image here. πŸ‘‡

Rerun the prompt. Several times. Image
Changing the aspect ratio to 9:16

I like this aspect ratio because I could create a video of it for YT or TikTok etc.

left
extreme close-up photo of a beautiful girl with red hair --ar 9:16

right
redheaded ImageImage
If you love the results, you can stop here.

Let's test by adding --style raw parameter.

I'm going to use "girl with red hair" moving forward. No significant difference between the two.

extreme close-up photo of a beautiful girl with red hair --ar 2:3 --style raw Image
Can you tell the difference?

v5.1 vs v5.1 style raw

Prompts in the ALTs.

I almost think I like the default 5.1 better. Although really subtle differences. extreme close-up photo of a...extreme close-up photo of a...extreme close-up photo of a...extreme close-up photo of a...
Next, I want to add stylize, just to see what effect it has (or not).

Left
extreme close-up photo of a beautiful girl with red hair --ar 2:3 --s 750

Right
extreme close-up photo of a beautiful girl with red hair --ar 2:3 --style raw --s 750 ImageImage
I rerun each several times.
Based on the results - personal preference, I like the 5.1 the best.

Stylize 750 adds quite a lot of flying hair...

For the next step, I'll use 5.1 - no extras.

Adding: eyes closed

I tried both --ar 2:3 and --ar 9:16
Liked 9:16 better. extreme close-up photo of a...
This prompt is still fairly basic. But it can generate amazing images!

I'll do another thread taking this prompt from here to more "advanced" or different places.

Here's a sneak peek.

#midjourney #aiphotography ImageImageImageImage

β€’ β€’ β€’

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

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, 2024
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. πŸ˜…
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, 2024
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, 2024
You can now edit your DALLΒ·E images in ChatGPT

It's basically inpainting/generative fill.

This is how to do it πŸ‘‡ 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, 2024
tile parameter in Midjourney - Tutorial

Including prompts.
πŸ‘‡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!

:(