Happy, Joyous, And Free Generative AI Video

I've been producing House music for a couple decades. After playing the label game for the past 10 years, I'm now happily self-releasing. This means I have much more control over my brand and creative. The large majority of my target demo is on Instagram, and I regularly create IG reels as part of each release's promotional assets. For my release, "Happy, Joyous, And Free," I decided to create a 40 second video using genertive AI.

My process

I wanted a visualization that had an endless, fly-through quality to match the looping, evolving vibe of the music. Something with a defined figure / ground, abstract yet concrete. I cracked open my dusty art history books from college and began looking at the work of some of my old faves: Giorgio de Chirico, Alberto Giacometti, and Robert Rauschenberg. I decided to create a shimmering, reflective sculpture on a beach, with bright blue skies and fluffy clouds.

The first challenge was to translate my vision into a prompt for Midjourney and get the sophisticated results I had in mind, i.e. cinematic, with specific lighting effects, and with the camera angle I envisioned:

Futuristic abstract heroic sculpture on beach. Surface is highly reflective, smooth, with wavey curves, forming a circle in the middle. High contrast neutral metallic colors. Beautiful blue sky with white clouds in background and ocean in the distance. Peaceful, serene, and dreamy mood. Eye level shot --ar 9:16

This prompt, along with several variations, produced a number of images I liked.

midjourney_keyscreens_v02

The next step was to generate video clips in Runway from the Midjourney stills. I used Runway's Gen-2 motion brush to add movement to the sculpture, and specified first and last keyframes to ensure a seemless loop. Finally, I added type elements and a bumper at the end that teased the album artwork.

Conclusion

This unboosted reel got 2494 plays, 617 replays, 52 likes, 17 comments, and 166 conversions to my Spotify. These aren't mind-blowing numbers compared to your average TikTok dance vid, however, I'm happy with the results.

I think we're in the very early days of generative AI. There were many morphing, melting, and bizarre Runway renders that I had to throw out. Still, the process was fluid and quick enough for me to iterate on the fly. With Midjourney, I had to force myself to revise the prompt instead of just photoshopping things I wanted to change. After a while I felt like I had a lot of control over the form and style of my imagery and really started enjoying the process.