Welcome to the “FIX” district, the once bright lights have long since flickered out here, leaving behind a dimly lit and desolate landscape. The air is thick with the stench of decay and desperation, as outcasts and drug-addled denizens shuffle aimlessly along the broken and littered terrace streets. Everywhere you look there are signs of our societal breakdown, and it has brought this dystopian world to its knees. From the shattered storefronts and burning buildings to the flickering neon signs advertising the latest designer drugs. Amidst this chaos, a black market thrives, fueled by the desperate search for the red pill that promises to unlock a better reality. But for everyone here, this escape remains an elusive dream, as the cycle of addiction and poverty grinds on relentlessly into the smog filled air.
I put a lot of love into this dystopia, I hope you enjoy it.
-TC
Introducing “Joans“, a virtual location from my “Byte’s Cypherpunk 2081” VR series, the most technical, intricate, and novel Equirectangular image series I’ve ever created.
This time around I had a number of Cyberpunk prompts saved and ready for scene generation in Blockade Labs. I explored far more detailed and intricate prompts for this cyberpunk scene, as I knew exactly what I was after. Once I successfully generated the background layer I went to work in Mid Journey. Here I spent the majority of my time, first I focused on generating full body portraits for the inhabitants of my scene. Using the background layer as a guide for specific lighting and color information that I could use to direct Mid Journey for these portraits. Next I began generating stray cat portraits based on where I thought they fit into the scene. After this I generated signs, flyers, objects, and paraphernalia that would complete the look. Once I had a collection of scene elements I ran the images through the AI upscaler by Topaz Labs. These exports were brought into Lightroom where additional details, highlights, curves, color, texture, and sharpness were applied to all the images including the Equirectangular image.
I added an additional layer of complexity to this scene with a layer of smoke, fog, and steam elements that gave this world the vibe I was looking for. With the background layer under the overlay grid in Photoshop I could simultaneously composite both the smoke and the individual high resolution objects and portraits into the scene. Just as before the imported smart objects were warped in Photoshop to convert them from rectilinear to Equirectangular projection.
The added smoke elements to my workflow were crucial in providing much needed atmosphere to the image. There was also an unexpected benefit from this layer as it provided a way to disguise some of the complex compositing layers under a layer of smoke which completed the illusion for me.
Due to the added layer of smoke and fog detail and the increased complexity of the scene inhabitants I lowered the master Equirectangular size down to 18,432 by 9,216. Editing in Photoshop and Lightroom at this scale was much more enjoyable with my current M1 Ultra configuration.
The extra layer of smoke effects were added in small groups as I blended them with the scene. I was careful to place them in accordance with the grid overlay system so their direction and size were convincing.
In order to edit in equirectangular space you need to change the image projection when importing a rectilinear image, this conversion needs to be done in a convincing way, so a grid overlay is used. High resolution rectilinear still images would be imported into photoshop converted to a smart object and then warped through Photoshop. For objects with heavy distortion fields near the Zenith and Nadir I placed and re-projected them with Pano2VR.
The Grid Overlay seen here represents distortions of a rectilinear view when projected in equirectangular space. Using the overlay helps keep distortions at a minimum when in VR and when viewing the rectilinear projection of the equirectangular image.
Carefully crafted prompt engineering is essential to the success of any AI generated project. Those who dismiss AI image generation as a simple prompting exercise do not understand the process of directing AI to very specific constraints. Lighting, color, depth of field, style, subject position, camera angles, seed numbers, and negative prompting, are all crucial to create a seamless composite across all images. Countless hours of practice with AI, and the concise economy of words used are required to keep the constraints consistent across all renderings.
Even with specific prompting you will undoubtedly need a healthy dose of patience and some re-rolling of prompts.
Example mid journey prompt: cyberpunk phoenix sign, detailed, elite, royal, circle shape, neon, dim light, yellow, teal and pink, sharp focus, top view –v 5 –ar 4:4
I owe a great deal of thanks to Sandra Cannon who first introduced me to AI language models through her artwork in 2022. I watched her battle cancer with creativity and art. It left a powerful in-print on me that I will never forget. Sadly Sandra and I never got to meet in person, but towards the end of her life she had begun to reach out and connect with me. Tragically Sandra passed away the same day I completed this project. I will never know if she received my message of gratitude so I’ve immortalized her in a tribute version of this image with the last photo she ever posted on facebook. Sandra Cannon will live on in our hearts and memories forever.
My deepest condolences to those who knew her and who miss her greatly,
With <3 -TC
