Aegis and the Seven Districts
A Marathon using Midjourney to Create Concept Art for Shepard's Tone
In this issue of The Brief, I'll be delving deep into the intricacies of utilizing Midjourney 5.2, a state-of-the-art design software, to craft the conceptual art for the sprawling city of Aegis and its seven distinct districts, all set to be showcased in the much-anticipated film, "Shepard’s Tone." Midjourney, with its enhanced features and tools, will allow me to bring to life the unique characteristics and atmospheres of each district, ensuring they resonate with the film's narrative and the director's vision. I'll be experimenting with the software’s capabilities, from its expansive palette of colors and textures to its advanced rendering techniques, all in the pursuit of capturing Aegis's essence. Join me as I embark on this captivating journey of visualization, translating words and ideas into tangible and vivid illustrations.
Aegis - the world of Phi. Architecturally, Aegis stands proudly atop a continental plateau, a towering 10,000 feet above the barren region that was once a vast ocean "The Wasteland". The city's edifices, carved by religious significance and environmental demands, are monolithic grey stone structures devoid of windows. Central to its layout are four critical zones: the religious hub, the palace, the Ostinatum (military) led by the resolute Commander Thalos, and the commerce sectors, all surrounded by seven distinct districts. Each district symbolizes a faction, emphasizing Aegis's history as a confluence of cultures spanning thousands of years. Their deeply entrenched traditions, foods, music, and religious interpretations reflect their varied ethnic backgrounds.
How did I achieve these results?
Creating that image of Aegis was honestly a marathon. Three days, and a whopping 1,000+ attempts on Midjourney just to nail down that one perfect shot. It’s made me rethink the efficiency of the software. I mean, it took about the same time as it would've for an artist to hand-draw it from scratch. But here's the kicker: once you get that initial image sorted out in Midjourney, everything after is a breeze. The challenging bit? The prompting. It's tedious and feels far from the creative process I'm used to. Instead of letting my artistic juices flow, I felt bogged down in semantics and code. Maybe it'll get more intuitive as the software evolves, but for now, it's hard to see traditional artists vibing with this approach.
Step 1: Mood Board Gathering Kicked things off by finding some pics that felt right for Aegis's vibe. Dumped them all in folders to keep things organized. I sourced about 100 images for this part.
Step 2: Getting Descriptive with Midjourney Popped each pic into Midjourney and hit that "/describe" button. It's kinda like asking the software, "Hey, what do you see here?" This took me 3 days.
Step 3: Playing Around with Descriptions Took those descriptive words from Midjourney and tried 'em out individually to see what came up. It's all about understanding how each word changes the image. This was part of that 3 days above. What was interesting is that I found many of the prompts useless, especially when the prompt was referencing an artist - which is interesting. Oddly what I found most useful was the “in the style of… and then put colors, or moods, or words that Midjourney seems to have as important phrases”
Step 4: Setting the Scene Needed the right base scene, like a cliff's shot, even if it had nothing to do with Aegis. Think of it as setting the stage. This took me 2 days of searching on the internet to get just he right image to block this scene. This really sucked and took forever. Although, without this step I would have never gotten this image.
Step 5: Picking Aegis's Look Grabbed a city image from Unreal Engine Marketplace kit (Temple of Insight) that I'll also be using in Unreal Engine. It's like shopping for a city's outfit. This is a bit of pre-planning on my part - I intend to eventually cut production costs by using existing kitbash kits as much as possible.
Step 6: Laying Down the Basics Wrote down the shot type, angle, brief description, camera settings, and that widescreen aspect ratio of 3840:1660 (which Midjourney reads as 2.39:1). There are tons of videos on this, but it’s important to get this right (see my examples below.)
Step 7: Balancing the Images Added the two main pics: one for the base scene and the other for the city look. Gave 70% importance to the scene and 30% to the city. This was a great deal of trial and errors - it takes patience to get this right.
Step 8: Upgrading the Description Tweaked my initial description with some snazzy words I found useful from my earlier tests.
Step 9: The Fun Tweaking Part Played around—shuffled words, adjusted image importance, and added or ditched some terms until it all felt just right.
Zooming Out
For each rendition of Aegis, an essential component of my creative process involved zooming out to visualize the broader perspective offered by Midjourney. By extending the frame and capturing Aegis from a more distant vantage point, I was keen to understand how Midjourney envisioned the city's sprawling expanse and its placement within a larger context. This approach proved invaluable for conceptualizing potential zoom shots, providing a comprehensive understanding of the city's landscape, and ensuring that every cinematic transition, from close-ups to wide shots, would be seamless and visually coherent.
Zooming In
Utilizing the established method from the initial Aegis image, I revisited the project to produce a more detailed, zoomed-in rendition. In this refined version, I incorporated specific instructions to introduce additional spires, domes, and various architectural elements, all aiming to accentuate a distinctive North African ambiance. This closer perspective not only provides a detailed insight into Aegis but also emphasizes its unique cultural and architectural influences.
The zoomed-in depiction of Aegis presented its own set of challenges and nuances, demanding another three days of meticulous work. This closer perspective was not just about magnifying the original, but truly diving into the intricacies, revealing the city's architectural marvels and the intimate stories its streets might whisper. Although this endeavor took time, the result was not just one, but several compelling images at this zoom level, each showcasing Aegis's rich tapestry of details, textures, and the essence that makes it so captivating.
Dunea District
Under Calida's leadership, the Dunea District, known for its "Festival of Sands", celebrates its desert heritage annually. Locals wear embroidered garments and rugged boots, hinting at desert tales. The district features the iconic “Dar Al Sahraa” building, safeguarding against sandstorms. Dunea's distinct dialect and music evoke its rich history, while its cuisine offers roasted nuts and dried fruits. Playing a mediating role in inter-district affairs, Dunea respects the Seraphim but seeks a stronger Palace council voice. Guided by Calida, they honor their past while looking ahead.
For the visual representation of the Dunea District, I incorporated an image from a KitBash3D kit titled "Medieval Market," priced at $99.00. This specific kit offers a rich tapestry of details that align perfectly with the ambiance I intended for the district. I envision using it primarily for medium-range establishing shots, capturing the essence and atmosphere of Dunea.
Let me know if you like the behind the scenes on the how to bits of this… I can do more of that if you find it valuable.
What is The Brief and Who should read it?
I release a weekly digest every Friday, tailored for professionals ranging from executives to writers, directors, cinematographers, editors, and anyone actively involved in the film and television domain. This briefing offers a comprehensive yet accessible perspective on the convergence of technology and its implications for the movie and TV industry. It serves as an efficient gateway to understanding the nexus between Hollywood and Silicon Valley.
Who am I?
I'm Steve Newcomb. Functionally, I’m a recovering Silicon Valley founder that is finally old enough to have a bit of care. I’m perhaps most recognized for founding Powerset— it was the largest AI and machine learning project in the world when I founded it. It was later acquired by Microsoft and transformed into something you might recognize today - Microsoft Bing. Beyond Bing, I had the privilege of being on the pioneering team that witnessed the inaugural email sent via a mobile device. My journey also led me to SRI (Stanford Research Institute), where we laid the groundwork for contemporary speech recognition technology. Additionally, I was a co-founder of the debut company to introduce a 3D physics engine in Javascript. I've held positions on the board of directors and contributed funding to massive open source initiatives like NodeJS and even the largest such project, jQuery. My experience extends to academia, having been a senior fellow at the University of California, Berkeley's engineering and business faculties. Recently, I ventured into Layer 2 internet protocols and assisted a company named Matter Labs in securing $440 million in funding to bolster their endeavors.
What am I doing besides writing these posts?
Typically, I allocate a year between groundbreaking ventures. My exploration for the upcoming project commenced in May 2023, and the sole certainty is its nexus with the film, television, SMURF, and AI domains. Sharing insights on my research endeavors helps me discern between feasible prospects and mere illusions. My hope is that for this venture, I appropriately consider the ethical and sociological repercussions.
If you are interested in contacting me, being interviewed, being helped, or yelling at me, my email is steve.e.newcomb@gmail.com.
These are fantastic and I insist you keep them coming!