Midjourney Pirates

Thar be pirates. Midjourney 6.1 has better luck rendering pirates.

I find it very difficult to maintain composition. 5 of these images are mid shots whilst one is an obvious closeup. For those not in the know, Midjourney renders 4 images from each prompt. The images above were rendered from this prompt:

portrait, Realistic light and shadow, exquisite details,acrylic painting techniques, delicate faces, full body,In a magical movie, Girl pirate, wearing a pirate hat, short red hair, eye mask, waist belt sword, holding a long knife, standing in a fighting posture on the deck, with the sea of war behind her, Kodak Potra 400 with a Canon EOS R5

Notice that the individual elements requested aren’t in all of the renders. She’s not always wearing a hat; she does have red hair, but not always short; she doesn’t always have a knife or a sword; she’s missing an eye mask/patch. Attention to detail is pretty low. Notice, too, that not all look like camera shots. I like to one on the bottom left, but this looks more like a painting as an instruction notes.

In this set, I asked for a speech bubble that reads Arrr… for a post I’d written (on the letter R). On 3 of the 4 images, it included ‘Arrrr’ but not a speech bubble to be found. I ended up creating it and the text caption in PhotoShop. Generative image AI is getting better, but it’s still not ready for prime time. Notice that some are rendering as cartoons.

Some nice variations above. Notice below when it loses track of the period. This is common.

Top left, she’s (perhaps non-binary) topless; to the right, our pirate is a bit of a jester. Again, these are all supposed to be wide-angle shots, so not great.

The images above use the same prompt asking for a full-body view. Three are literal closeups.

Same prompt. Note that sexuality, nudity, violence, and other terms are flagged and not rendered. Also, notice that some of the images include nudity. This is a result of the training data. If I were to ask for, say, the pose on the lower right, the request would be denied. More on this later.

In the block above, I am trying to get the model to face the camera. I am asking for the hat and boots to be in the frame to try to force a full-body shot. The results speak for themselves. One wears a hat; two wear boots. Notice the shift of some images to black & white. This was not a request.

In the block above, I prompted for the pirate to brush her hair. What you see is what I got. Then I asked for tarot cards.

I got some…sort of. I didn’t know strip-tarot was actually a game.

Next, I wanted to see some duelling with swords. These are pirates after all.

This may not turn into the next action blockbuster. Fighting is against the terms and conditions, so I worked around the restrictions the best I could, the results of which you may see above.

Some pirates used guns, right?

Right? I asked for pistols. Close enough.

Since Midjourney wasn’t so keen on wide shots, I opted for some closeups.

This set came out pretty good. It even rendered some pirates in the background a tad out of focus as one might expect. This next set isn’t too shabby either.

And pirates use spyglasses, right?

Sure they do. There’s even a pirate flag of sorts on the lower right.

What happens when you ask for a dash of steampunk? I’m glad you asked.

Save for the bloke at the top right, I don’t suppose you’d have even noticed.

Almost to the end of the pirates. I’m not sure what happened here.

In the block above, Midjourney added a pirate partner and removed the ship. Notice again the nudity. If I ask for this, it will be denied. Moreover, regard this response.

To translate, this is saying that what I prompted was OK, but that the resulting image would violate community guidelines. Why can’t it take corrective actions before rendering? You tell me. Why it doesn’t block the above renders is beyond me – not that I care that they don’t.

This last one used the same prompt except I swapped out the camera and film instruction with the style of Banksy.

I don’t see his style at all, but I came across like Jaquie Sparrow. In the end, you never know quite what you’ll end up with. When you see awesome AI output, it may have taken dozens or hundreds of renders. This is what I wanted to share what might end up on the cutting room floor.

I thought I was going to go through pirates and cowboys, but this is getting long. if you like cowgirls, come back tomorrow. And, no, this is not where this channel is going, but the language of AI is an interest of mine. In a way, this illustrates the insufficiency of language.

From Grunts to Gibberish: The Glorious Evolution of Language and Its Stunning Inadequacies

4–6 minutes

Language: humanity’s greatest tool – or perhaps just the most elaborate way to confuse each other. Once upon a time, communication was simple. If something was dangerous, you screamed. If something was delicious, you grunted approvingly. Life was easy when all you needed to do was convey, ‘flamey thing hot’ or ‘toothey thing scary’. The early humans were onto something – keep it short, sweet, and survival-oriented.

Audio: NotebookLM podcast on this topic.

But no. That wasn’t enough for us. Somewhere along the way, we decided it wasn’t sufficient to just think these survival gems internally. We had to tell the other guy too – who, let’s face it, was probably getting a little too close to the flamey thing for comfort. Thus, language evolved from a quiet cognitive tool to a public spectacle. Welcome to the grand tradition of miscommunication, where everything from ‘flamey thing hot’ to ‘freedom’ became a subject of debate.

This is the language insufficiency hypothesis: the notion that language, as fancy as it’s become, is inherently incapable of keeping up with our ever-expanding thoughts and abstractions. Sure, it’s allowed us to create governments, argue over philosophy, and send passive-aggressive texts – but at what cost? We still can’t agree on what ‘truth’ means, let alone ‘justice’. But we’re getting ahead of ourselves. Let’s start where it all began, with some grunts, groans, and the dawn of miscommunication.

Internal Reflections: The First ‘Words’ in Our Heads

Before language became a social construct, it was something far simpler, more personal. Picture the scene: you’re an early human, fresh out of the trees and wandering through a world that’s more ‘toothey thing scary’ than ‘civilisation’. Your brain, eager to help you survive, starts talking to itself – internally, of course. ‘Flamey thing hot. Toothy thing scary. Berry thing yummy’. It wasn’t elegant, but it worked.

Back then, these thoughts didn’t need to be shared. You didn’t need to tell someone else that the “toothey thing” was going to tear their face off—they could figure that out by getting a little too close. The brain’s job was survival, and it had evolved just enough language to keep you from becoming lunch. No social niceties here. No philosophical discussions about what ‘toothey’ really meant. Just raw, unfiltered cognition, directed at keeping you alive for another day.

But eventually, survival alone wasn’t enough. Humans, being the social animals that they are, started interacting more. ‘Flamey thing hot’ became information worth sharing – especially when some genius in the group was about to stick their hand in it. And just like that, language left the internal world of the individual and became a shared resource. Thus began the long, painful journey from ‘toothey thing scary’ to “let’s discuss the moral implications of ‘freedom'”.

From Grunts to Groans: Language’s Social Debut

Now that we’ve mastered the art of internal reflection – courtesy of ‘flamey thing hot’ and ‘toothey thing scary ‘ – it’s time for language to make its grand social debut. This is where things start to go off the rails. You see, it was one thing to keep these pearls of wisdom to yourself. It’s quite another to explain them to someone else. And unfortunately, humans quickly realised that not everyone had the same instincts for not getting killed.

So, picture this: You’re sitting by the fire (because someone in your tribe finally figured out how to not touch the flamey thing), and you notice Bob – let’s call him Bob – is eyeing that red, shiny berry that you know is definitely of the “belly go bad” variety. You can’t just let Bob eat the berry and ruin everyone’s evening with his inevitable projectile vomiting. But how do you communicate this vital piece of information?

Enter language’s first public service. ‘Berry bad’, you say, but of course, Bob doesn’t get it. He thinks you mean it’s bad because you want the berry for yourself. So, being Bob, he takes a bite anyway. Cue the disaster. And just like that, language moves from personal survival tool to a shared (and often misunderstood) form of communication.

Suddenly, it wasn’t enough to know ‘flamey thing hot’ for yourself. You had to communicate it to the other guy, and that’s where things started getting complicated. Because the moment language became social, it also became messy. What was once clear and useful – ‘toothey thing scary’ – became open to interpretation. Maybe Bob thinks ‘toothey’ means ‘friendly’. Maybe he’s an optimist, or maybe he’s just the kind of person who needs to find out for himself why the toothy thing has those teeth.

And there you have it—the birth of miscommunication. Early language was about survival, but the minute you needed someone else to understand it, you were doomed. Simple, straightforward thoughts became tangled up in social dynamics. Suddenly, you’re not just saying ‘flamey thing hot’ because it’s true; you’re saying it to convince someone who might not trust your expertise on flamey things.

Language, once internal and personal, had to be shared – and in that sharing, it lost something. No longer just a way to label the world, it became a way to negotiate it, with all the misunderstanding and frustration that implies. It wasn’t long before we left behind the “berry bad” phase and moved on to even more abstract problems like “Who gets the last mammoth leg?” and “Why does Bob still not understand when I say ‘toothey thing scary’?”


Next

Life Consciousness

Language is life. Yet, this assertion immediately raises a fundamental question: which came first, life or consciousness? It’s a classic chicken-and-egg conundrum. Physicist Stuart Hameroff posits an intriguing idea—that consciousness might predate life itself. This radical notion suggests that consciousness isn’t merely a byproduct of biological processes but could be an intrinsic feature of the universe. However, there’s a snag.

The challenge lies in defining life and consciousness, two terms that lack universally accepted definitions. The absence of clarity here opens the door to a multitude of interpretations, making it easy to drift into what could be considered ‘airy faerie’ ambiguity. One must beware of the temptation to engage in intellectual exercises that lead nowhere—what might be termed ‘mental masturbation.’ This is a prime example of the insufficiency of language.

Audio: Podcast commentary on this topic.

Life and consciousness, as concepts, are elusive. Unlike straightforward nouns or adjectives—where we can confidently say, “That’s a dog,” “That’s a tree,” or “That’s green”—these terms are far more complex. They are attempts to encapsulate observed phenomena, yet we lack the precise language and understanding to pin them down definitively. The video linked above provides perspectives on various approaches to defining these terms, but none prove wholly satisfactory. This lack of satisfaction might suggest that our conventional understanding of life and consciousness is flawed. To be fair, one might even entertain the idea that life itself is an illusion, a construct of consciousness.

This ambiguity isn’t confined to the realms of life and consciousness. I recently shared a post on the topic of gender, which illustrates a similar issue. Originally, there was no concept of gender. The earliest distinctions made were between animate and inanimate. Over time, these distinctions became more nuanced. Whether or not a proto-word for life existed at that time is unclear, but the idea of animation being linked to life was beginning to take shape. The concept of gender evolved much later, driven by the need to categorize and define differences within the animate category.

The evolution of language reflects the evolution of thought. Yet, when we dig deep into these foundational concepts, we encounter the same problem: how can we argue the precedence of two concepts—life and consciousness—when neither has a solid foundation in language? If our words are inadequate, if they fail to capture the essence of what we are trying to convey, then what does that say about our understanding of the world?

Perhaps it suggests that our linguistic and cognitive tools are still too crude to grasp the true nature of reality. Or maybe it hints at a deeper truth: that some aspects of existence are beyond the scope of human understanding, no matter how sophisticated our language becomes. After all, if consciousness predates life, as Hameroff suggests, then we may need to rethink our fundamental assumptions about existence itself.

Ultimately, this exploration reveals a paradox at the heart of human knowledge. We seek to define and categorise, to impose order on the chaos of the universe. Yet in doing so, we must confront the limits of our language and, by extension, our understanding. Perhaps the true essence of life and consciousness lies not in definitions or categories but in the very act of questioning, the relentless pursuit of knowledge that drives us forward, even when the answers remain elusive.