Thoto × A$AP Rocky Tour

At 5:44 PM EST, two close friends and I opened a group chat to brainstorm. That is where the creative direction got built. Friend-1 steered the vibe right away: army, not SWAT. They dropped reference boards and handed me the client question list, hammering that the songs mattered most.

The direction came together fast: army not SWAT, grunge, heavy haze and smoke, glitchy strobe, a hint of CCTV. Soldiers with guns, selectively, with red lasers off them. Helicopter propeller blades as scene transitions. Then I steered it into what I would actually build.

Mood board

The board the three of us pulled together: red HUD scopes, surveillance and CCTV, black-and-white targeting, glitch, smoke. I built straight toward this.

References collected on Pinterest, full credit to the original creators. View the full board →

LXND bit within about five minutes on Instagram. I called instead of texting back. They told me exactly what they wanted: soldiers walking toward the camera, a battlefield war-zone vibe, and to swag it out. The visuals were for Thoto, an opener on the A$AP Rocky tour, covering Thoto's whole set.

On that same call I pinned down the environment, the colors, the soldiers' outfits, and sent the mood board to confirm direction. They locked it to a single QR code, and the visuals had to carry every song of the set, not score one track. LXND gave me the screen spec: 1920×1080, horizontal.

The proposal PDF

I started thumbnails with one AI image tool. Not realistic enough. So I jumped to a better one, ran the same prompts plus variations, and got stills I loved. Then I brought each still to life as AI video, directing it shot by shot. Usable motion, fast.

First AI pass (scrapped, not real enough)

Better AI (the win)

The shot list

I couldn't just have them walking at the camera, I needed real angles.

Squad advancing toward camera (top-down)

Lone soldier walking toward camera into a red explosion

Black-ops face, quad night-vision goggles

Three soldiers through red smoke (top-down)

Advancing through the bomb blast

Black-ops face, second variation

Boot through the red smoke (side angle)

Tank tread, made but cut for time (saved for the next show)

The QR codes came through as dark black-gray on transparent. To read clean against a dark scene, I vectorized one and recolored it white, then carved a space into a soldier's back vest and placed it there. I built an in frame and an out frame and fed both to a more powerful AI. Give that AI one endpoint and the code gets mangled and will not scan. Both endpoints keep it sharp.

Before: the original dark gray, low contrast against the dark scene

Fixed: vectorized + recolored white in vector software

Image-editing software: the QR code built onto the back vest (in frame)

A more powerful AI: the out frame, animated in-point to out-point to keep the QR code scannable

Then I timed the QR code.

They wanted the QR code up once a minute, but my loop was only 25 seconds with the code at the very end. In the final comp I duplicated the loop across the full 10 minutes and stripped the code off every other pass.

Comp 3: the final 10-minute assembly, the 25-second loop duplicated with the QR code kept on every other pass (the alternating colors) so it lands about once a minute, for exactly 10 minutes

It started all red, following the Rocky vibe and my mood board. Then LXND and Casper both hit me to switch it to green, and I was already deep into red. My fix was two compositions: a movement comp holding the chopped clips, and a final comp at 1920×1080 matched to the pixel map. I dropped the first inside the second and applied a single hue rotate. Everything flipped in one move.

Comp 1: the raw clips clipped together in the compositing timeline

Then I hand-treated it.

In that same final comp I hand-treated the whole thing. Curves of calculated blur riding in and out. Monochrome grain pushed and pulled so it breathed like CCTV footage. Each shot fading up from black and back down, so the loop never cut harshly.

Comp 2: the final comp, the movement comp dropped inside with the red-to-green hue rotate plus the grain and blur treatment stacked on top

Casper, on the media team, only had the logo as a video with its own colors baked in, which did not match the look I was building. The source files could not come through in time. So I screenshotted a frame, lifted the logo out with my own software, and rebuilt it as a clean PNG and SVG. The custom 3D version ran out of clock and became a next-show item.

Source: the LXND logo, sent as a 3D video with colors baked in

Pulled + cleaned to a PNG / SVG

16:9NextPlanned 3D logo asset matched with real-time environment lighting (for the next show).

I exported the final loop, then a ten-minute version, the length of Thoto's set. I uploaded everything to their Dropbox, every file named so they knew which was which. Fully uploaded by 9:20 PM EST. From 5:44 PM EST to delivery, about a three-and-a-half-hour sprint.

That obsession with staying organized is why I built my agents the way I did. They read my raw files, rename them, sort them into a client file system, and set up the delivery folder. Even on a chaotic same-night turnaround, nothing got lost.

The client file system, every clip cleanly named and sorted

The Dropbox handoff, the final loop + 10-min version, cleanly named

The loop ran for Thoto's full set. Soldiers walking toward the camera. The full compositing treatment. The in-world QR code showing up once a minute. All at 1920×1080, built and delivered in a single night.