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.

more 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. 😅

https://x.com/DeryaTR_/status/1789052890566259009

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. 1. Go to

2. Choose or create a character
- I chose Alice rendernet.ai/app

You can now edit your DALL·E images in ChatGPT

It's basically inpainting/generative fill.

This is how to do it 👇 1. Click on your ChatGPT generated image to open the editor.

tile parameter in Midjourney - Tutorial

Including prompts.
👇 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 pattern

AI Image Upscaler Comparison

Paid and Free.

Let's compare.

Closeup of the original MJ image. 1) 2x Midjourney Upscaler

Midjourney vs. Dalle-3 vs. Adobe Firefly

Same prompt for all.

10 spicy examples.

1. 2.

Dalle-3 access in ChatGPT-4 keeps rolling.

If you don't have access yet or just got it, this is for you.

10 outstanding examples and helpful observations. 1) When you get access - thoughts and examples

https://twitter.com/dr_cintas/status/1709642253025652771

Is there a winner?

I ran several of my prompts through both MJ and Dalle 3.

11 interesting comparisons 👇 1)
None of the MJ outputs had a confused look.
All of Dalle's did.

Bing Chat vision with DALLE 3 is wild.

I gave it my drawing.

This is what happened. 1. I dropped my drawing into Bing Chat (creative option selected).

I asked it to describe the image and explain what it might mean.

P.S. The meaning wasn't exactly on point.

48+ hours since Chat GPT-4V has started rolling out for Plus and enterprise users.

Incredible use cases and potential.

10 of the best examples I've seen. So far... 1. Education

https://twitter.com/mckaywrigley/status/1707408491110080602

You've probably seen these types of marbled backgrounds.

They are popular, and they look amazing!

This is how you can create them in Midjourney. First, I have some excellent news!

There are several prompts/prompt variations to get these results! MJ does an excellent job with these.

Depending on what words you use, you can see slight differences.

abstract, fluid ink washes, [color] and gold, kintsugi
I used magenta

Aspect ratios affect portrait compositions in Midjourney.

Using different aspect ratios can change the framing of 'portrait' shots.

To see this in action, let's decode a fairly simple and isolated prompt of a Japanese supermodel. The prompt:
portrait of a Japanese supermodel, big glasses, Y2K aesthetics, chrome, icy blue, neon pink, glossy white, fashion photography

I generated 100 images for each of the aspect ratios to better study the effects.

P.S. I will go over a token in this prompt tomorrow.

New Midjourney 'feature' - Aug 23,2023

Remaster your old images

Shout out to @WorldEverett for noticing.

Not sure how long this has been up 🙃

Let's take a look.

There are a couple of ways to do this.

The prompt is below, too. 👇 Method 1: Remaster an older upscaled image

If you have an image e.g. v5 that you have already upscaled, do this.

1. Copy the job ID of the upscale

I did this on the Midjourney website going to my archives and choosing the upscaled image I want to remaster.

Prompt share:

Here's a quick example of how you reduce the busyness of an image.

Starting prompt:

Oracle, graphic illustration, light gold and indigo --ar 16:9

Midjourney v5.2 To reduce busyness - add: minimalism

Prompt:
oracle, graphic illustration, light gold and indigo, minimalism --ar 16:9

Note:
This prompt creates quite a range of images. You can test it yourself - a wide range, but all pretty minimalistic.

Learn Prompting - Midjourney

No. 1
Making changes to a prompt

One of my creative workflow.

I'm going to use this prompt as an example:

data, analysis, graph, sci-fi, future, background, blue glow color, orange, hologram, city --ar 3:2 https://t.co/YUEOT7iipWtwitter.com/i/web/status/1…
Once you have a prompt that generates the output you want or a prompt e.g. from a prompt share - start changing things up.

Here I simply changed orange to yellow.

Multi Prompts - Midjourney Tutorial

Advanced Prompts
Adding a :: (double colon) to a prompt tells Midjourney Bot to consider each part of the prompt separately.

Let's take a look.

Thread. twitter.com/i/web/status/1… Multi-prompting works on all MJ versions.

I'm starting with this prompt:
closeup shot of an alien princess, green slime, hyper realistic --ar 16:9

Adding Chaos (Midjourney)

Here's a quick tutorial about how adding the chaos parameter affects the grid of images.

Default chaos is zero.
Max is 100.

Base prompt:
close-up shot, mushroom, fractal --ar 16:9

Thread.

#midjourneyv51 #midjourney5 First image.
This is what MJ says about --chaos or --c parameter.

Second image.
Close-up shot, mushroom, fractal --ar 16:9
No chaos.

Prompt Share

Do I have something for you... 😍

As usual - insanely simple base prompt.

The base:
"candid photo"

Then you can start adding things to it...

For example:
candid photo of a woman [add aspect ratio of your choice]

- you'll get both young and old twitter.com/i/web/status/1… candid photo of a young woman
or
candid photo of a 20-year-old woman

How to build a prompt

Midjourney v5.1

- but the same principle can be applied to other versions and AI image generators (although prompt elements/tokens may need to be adjusted)

Start with the minimal elements possible and build it one "block" at a time.

Thread. twitter.com/i/web/status/1… The starting point:

Subject + style

The subject: "a portrait"

I have an idea that I want to combine two styles:
1. minimalism
2. pop art

I'm first running each separately.

The prompt:
a portrait, minimalism --ar 16:9
and
a portrait, pop art --ar 16:9

Monetizing AI - YouTube

I'm getting questions about how to monetize and make money with AI - whether with images you generate or otherwise, so here's the first installation of the series "Monetizing AI."

Thread. twitter.com/i/web/status/1… How do you make money with AI on YouTube?

- AdSense (YouTube partner program)
- memberships
- super chats (live streams)
- merch
- brand deals

👉There are many ways to make money on YT

Working a Prompt - Midjourney

The promised process of how to generate images like this 👇👇👇

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. 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.