Tag: Midjourney

  • AI & Creative Process

    Generative AI makes almost anything possible. You just need to know the tools and be clear about what you want to say.*

    [*In addition to it, you’ll of course need motivation, agency, and taste, but let’s save this discussion for next time.]

    For better or worse, art/culture is about to change, and I’m changing with it.

    For the context: Among other things, I’m also a “real artist”, aka an artist who has been creating without AI – for quite some time. Luckily, I’m very pro-tech (grew up with computers thanks to my dad), and have no unresolved conflicts pertaining to creativity, which is why I’ve experienced a pretty smooth conversion from “real art” to AI content.

    I’m mentioning this because a huge chunk of “real artists” continues to be outraged about AI. But that’s something for a future blog.

    In the past few months I’ve been using AI to create a lot of stuff (see “Projects”). Since I’m very active on Twitter/X (by the way, let’s connect), I tend to learn about new tools very early, and in many cases I head straight to the tool to try it out.

    General Observations

    Experimenting, or as some call it “tinkering”, is essential. We are entering a new terrain of artistic expression, with a lot (most?) of it still unexplored.

    Imagine what it must have felt like when photography was invented. As cameras became more accessible and photography moved from early adoption into the mainstream, people began to test its boundaries. 

    They didn’t just replicate paintings. They played with light, blur, composition, even accidents. That’s how entirely new aesthetics emerged.

    The same applies to AI tools today. The real breakthroughs don’t come from following tutorials step by step, but rather from misusing tools, playing with prompts, layering outputs, remixing styles, and exploring the “wrong” ways of doing things. 

    Tinkering isn’t aimlessness, it’s a tool of discovery. 

    It’s how genres are born, how formats mutate, and how we can stretch the limits of what feels possible.

    What I’ve Learned

    Things are changing fast, but for the foreseeable future these insights will probably hold true.

    Assuming you want to enter the space and try creating something, 

    • Many platforms offer free daily credits, and you should make use of those.
    • Have a structured collection of AI tools. In my case it’s a bookmarks folder.
    • Definitely also structure your computer folders. You might end up with a lot of images and videos. Don’t get lost in the jungle.
    • Spend time away from your computer and write down your ideas on paper. In my case being in the nature really helps to not get lost in the detail. 
    • Recognize the difference between “gimmick” and “substance”.  I see people post AI videos on X, and most of them are gimmicks (= they don’t have any message, and/or are just tropes). Now you don’t have to have ambitions to create anything of substance. But some discernment really helps here either way.
    • Spend some time thinking about taste and what it implies. 
    • Have ChatGPT write your image / video prompt. Your job is to tell it your idea, intent, message. This middle step adds a big layer of detail.
    • Get familiar with JSON. Prompts in JSON format are the ideal language when talking to AI.
    What a prompt in JSON format looks like. This one is for a video.

    I will surely dedicate another post to the insights I’ve had while using all the different AI tools. For now let’s keep it concise. 

    Finally, below is a list of some of the AI tools I’m using. Give them a try; they all have a free tier.

    AI Tools I Use

    Voice & Script Generation: I use Google’s NotebookLM, a free tool that transforms PDFs, websites, or text into audio summaries. This makes scripting and voice generation easy, even for complex topics. For cases when I need a custom voice (and for all things text-to-speech), Elevenlabs is my go-to.

    Music Creation: Tools like Suno and Udio enable me to generate background music for any mood, or entire songs, if I happen to have any song idea. You can use lyrics or create instrumental tracks.

    Video Generation: Platforms such as Runway, Luma, and Kling AI allow video creation and animation, offering a variety of capabilities depending on the project. These days I also increasingly use Dreamina by ByteDance/CapCut.

    Image Generation: I prefer Ideogram, Flux, Reve, and Leonardo.ai for diverse artistic styles. ChatGPT image generation is great for Ghibli-style illustrations or comics. Unlike Midjourney, which tends to create polished, predictable images, these tools yield more unexpected and raw visuals, perfect for experimental art.


    That’s it for now! If you want to *listen* to me talk about my creative process, here’s a video I made some time ago:

  • Midjourney Through Directors’ Styles: Tarantino, Aronofsky, Kubrick etc.

    Midjourney Through Directors’ Styles: Tarantino, Aronofsky, Kubrick etc.

    I love looking at unique characteristics of various directors’ styles. This exploration led me to an exciting experiment: I entered the prompt “two men staring at each other in shock” into Midjourney, and specified that the scene should be written “in the style of (director) “. The directors I chose for this experiment were, among others, Tarantino and Aronofsky, each renowned in their own right, but with starkly different storytelling styles.

    The interesting thing is, in many of these images the men are not staring at each other, but instead at the camera. I guess Midjourney doesn’t care that much about the direction of the gaze. I also asked ChatGPT to write a paragraph for each director’s frame. Somehow ChatGPT’s output was surprisingly accurate, even though it couldn’t see the images.

    Tarantino

    Quentin Tarantino, known for his eclectic and often non-linear storytelling coupled with detailed character development, has a unique way of framing even the simplest of scenes. His narratives are filled with intense dialogues, heightened violence, and a touch of dark humor. When the AI was asked to interpret the prompt “two men staring at each other in shock” in the style of Tarantino, it generated some pretty

    “Clarence and Sonny, two weathered gun-slingers, find themselves in a dingy bar, the air thick with tension. Sonny’s cigar smoke swirls in the air as his hand hovers over his holster, his eyes locked onto Clarence’s. Clarence, on the other hand, is a statue, his icy gaze never leaving Sonny’s. Suddenly, a roach skitters across the bar top, breaking the silence. Both men jump, their hardened facades crumbling as they share a look of pure, unadulterated shock. A moment of shared vulnerability in an otherwise deadly game of cat and mouse.”

    Aronofsky

    Darren Aronofsky, on the other hand, is known for his dark, psychological narratives, often dealing with themes of obsession and the human condition. His characters are complex, their inner turmoil often taking center stage. The following is the AI’s interpretation of the same prompt, “two men staring at each other in shock”, in the style of Aronofsky:

    “Elijah and Jonah, two estranged brothers, stand in a dilapidated room, the remnants of their shared childhood echoing in the silence. The peeling wallpaper, the dusty pictures, all bear testament to happier times. When Jonah reveals a long-held family secret, the impact is immediate. The brothers stand, eyes wide, their shared shock reverberating through the room. Their personal demons are laid bare, and in this moment, their shared grief becomes a tangible presence.”

    Emmerich

    Roland Emmerich, the master of the disaster film genre, is known for his grand-scale narratives with a focus on survival amidst catastrophe. When ChatGPT was asked to interpret the same prompt “two men staring at each other in shock” in the style of Emmerich, the result was:

    “Amid the rumble of an impending disaster, scientists Robert and Daniel stand in the control room, surrounded by flashing screens and blaring sirens. They’ve just realized that their calculations were not just a theory anymore – the catastrophe is imminent. They stare at each other, their faces pale, their shock mirroring the intensity of the situation. The countdown to survival has begun.”

    Kubrick

    Stanley Kubrick, revered for his meticulous attention to detail and symbolic storytelling, often explored themes of humanity and dystopia. When asked to interpret the prompt in the style of Kubrick, ChatGPT spun the following:

    “In a sterile, futuristic room, two androids, Adam-7 and Eve-8, analyze a forbidden piece of human history – an abstract painting. They exchange a look of shock as they process the chaotic swirls of emotion, a concept alien to their programming. Their shock signifies the dawn of a new understanding, a breach in the otherwise perfect order of their existence.”

    Wes Anderson

    Wes Anderson, recognized for his whimsical narratives and distinctive visual style, crafts a world that is both familiar and surreal. His characters often find themselves in odd, humorous situations. The AI’s interpretation of the prompt in Anderson’s style reads:

    “Inside the quirky, pastel-colored bakery, Francois and Gustave, two competitive bakers, witness their experimental ‘Volcano Cake’ unexpectedly erupt, splattering the pristine pink walls with chocolate lava. Their eyes meet in shock, only to be followed by a burst of laughter. Amid the mess, their rivalry melts away, replaced by the sheer absurdity of the situation.”

    Spielberg

    Steven Spielberg, one of the most influential directors in the history of cinema, is known for his heartwarming narratives and iconic cinematic sequences. His stories often center on themes of wonder, adventure, and the triumph of the human spirit. When the AI took on Spielberg’s style, it created:

    “Inside a secret government lab, young prodigies Sam and Max accidentally activate an ancient alien device. A spectral figure flickers to life, its presence a testament to civilizations beyond their imagination. They stare at each other in shock, their eyes wide with fear, wonder, and the thrill of the unknown. Their childhood adventure has just taken a turn into the extraordinary.”

    Gaspar Noé

    Gaspar Noé, an Argentine filmmaker, is renowned for his provocative and visceral narratives, often exploring the darkest corners of human nature and society. When the AI was tasked with interpreting the prompt “two men staring at each other in shock” in the style of Noé, it generated:

    “In a grimy underbelly of the city, drug addicts Kino and Remy share the last of their stash. As the hallucinogenic effects kick in, reality warps and the mundane becomes horrifying. They stare at each other, their faces twisted in shock, fear, and a dawning realization of their descent into oblivion.”

  • Pope Francis Spotted on the Sidewalk at Night

    Pope Francis Spotted on the Sidewalk at Night

    Was he buying cigarettes, or coming back from a club? A photo has surfaced on social media showing Pope Francis walking alone on a city street at night. The photo, which appears to have been taken with a smartphone, has sparked controversy and raised questions about the safety and security of the pontiff.

    The Vatican has not yet commented on the photo, but many are speculating that the Pope may have been attempting to escape the confines of the Vatican and experience life outside the walls of the holy city. Others are concerned that the Pope may have been putting himself in danger by wandering alone through a city at night.

    In case you hadn’t already noticed: The above text is fake, and so is the image. It sounds like a win for BuzzFeed and the likes, for its entertaining value, but it can will also lead to deteriorating trust towards the media. Towards ANY media! Because I’m feeling like having silly fun today, I’m going to add some fuel to the dumpster fire.

    Some of you might have heard of the famous “Pope Drip” meme, depicting the current Pope wearing a Balenciaga puff jacket. This image has obviously been generated by Midjourney, but perhaps we all wish it would be real.

    And here is a prompt that can be used to create it:

    AI is cool, but it can also deceive, and so far I can’t even imagine the consequences of the mass freakshow that’s about to hit us. Below are my own little Pope Francis deepfakes (sorry, world) aka contribution to the chaos. The Age of Disinformation is in its infancy, and how are we going to verify anything in the future?

    But anyways, let’s continue where we left off. Here are some more images of the Pope that I made:

    Pope Francis and Kanye West in a taxi

    Here once again Pope and Ye, but this time drunk:

    Drunk Pope and Kanye

    Pope Francis with face tattoos:

    Pope at a burger eating contest:

    Pope at a Burger contest - Swetlana AI x Midjourney
    Yummy

    Here’s one more because why not:

    Aand here he is at a fashion show wearing sunglasses:

    And why stop at Pope Francis? Here’s a photo of Barack Obama and Angela Merkel getting married: