The Heart of Screenland is a playable film production. Teams race through Culver City performing scenes on their phones, and video-to-video AI turns those performances into a community-made short film, produced and released on the same day.
Fun leads to Everything Can we make a scavenger hunt fun while interleaving it with skits powered by the most advanced video-to-video AI workflows?
VIDEO
The City is the Screen On May 29, 2026, we hosted GEN HUNT: The Heart of Screenland at AI on the Lot, the largest AI media tech conference. I worked with Jay Judah, Adam Mutchler, and the extended network of Machine Cinema in Los Angeles. Jay Judah asks us to imagine a temporal rift has opened, causing Culver City's film history to spill into the present: an experimental short exploring how we might interact with the media of the past.
For a century, Culver City has been called "The Heart of Screenland." For one hour, its streets became the soundstage. Six teams met at the Culver Steps and raced to ten locations. Every scene came with a location, a character, a voice and a line of dialog. Teams filmed a short horizontal take, then optionally added a director's note about what the scene should look like. You could say whatever you wanted, but if you went off script and broke the story beat, the story owner would likely reject the take. The audience performs; the producers keep authorship of the story.
Built for the Live Experience A few weeks before the conference, 10zebra built out the generative workflows, the game experience, and the admin portal to oversee and create new scavenger hunts. Players never touched a node graph or installed an app. Through a series of tests with volunteers and across the core team, we iterated on capture, omni model providers, system prompts and live pre-viz. There were many awkward videos of 1930s police officers running around snowy streets with the voice of a young girl. Voice morphing, stuttering, character blending: all hurdles to overcome. Even from a month earlier, we came a long way. Compare it to our pilot experiments with GAN models many years ago? Night and day.
"The future that we dreamed of and built for - it's finally here." - Philip Meier, Founder of 10zebra Produced and released the same day During the scavenger hunt we could watch our live portal convert the script into community-generated video. Every time someone filmed a new version of Scene 4, it replaced the previous version of THE PIANIST in the SPEAKEASY, and everyone could watch it on the next loop. The reel always looped back to the beginning, so as more of the story was completed, the draft narrative grew longer and longer. Eventually our live draft covered the script: 10 scenes, 10 lines of dialog, 150 generations from six teams. That evening, the community cut was released to participants in the app and screened at the AI on the Lot afterparty.
Watch the live feed:
What the performances proved Can different people act out different lines, and still look like the same character? Yes.
Different actors delivered the same line, of the same character, with directors notes.
Can they also sound like the same character? Yes.
Can we capture nuance of their pacing and intonation? Yes.
Can we capture their postural motions and transfer them to the generated scene? Mostly. Sometimes. It depends what action they do, and a complementary prompt really helps. We call them director's notes, and they help your make-believe actions land as believable in the narrative world, rather than looking like awkward movement. How are they used? Director's notes are instructions that are "interpreted" by the software and provided as auxiliary information to a multimodal "Omni" model. We don't build these models, but we support all the major ones. Our contextual management makes it easier to manage your acting with respect to a story.
In this example, one team paired their acting using the Directors Notes to inject a woman with bunny ears into the scene. Everyone laughed. That take did not make the cut. Actors make the difference If you have not noticed it yet, there is a coming tsunami of AI-generated content, and we foresee that audiences will identify with the craft behind the work. Automated content saturates. Software without effort lacks struggle and the layering of human intention. How you made it - and what it's about - become increasingly important, above and beyond what it looks like. At 10zebra we believe this means engaging meaningfully with actors, values-based brands, fans and community members.
Thank you everyone who helped us put this event together: Giulianna Gasparotto, Rachel Leventhal, Anina Net, Sean Ward, David Ronan, Machine Cinema, and Ai On the Lot.
Can different people act out different lines, and still look like the same character? Yes.
Can they also sound like the same character? Yes.
Can we capture nuance of their pacing, and intonation? Yes.
Can we capture their postural motions and transfer that to the generated scene? Mostly. Sometimes. It depends what action they do, and a complimentary prompt really helps . We call them directors notes, and they help your make believe actions land as believable in the narrative world, vs looking like awkward movement. How are they used? Directors notes are instructions that are "interpreted" by the software and provided as auxiliary information to a multimodal "Omni" model. We don't build these models, but we support all the major ones. Our contextual management makes it easier to manage your acting with respect to a story.
If you have not noticed it yet, there is a coming tsunami of AI generated content, and we foresee that audiences will identify with craft behind the work. Automated content saturates. Software without effort lacks struggle and the layering of human intention. How you made it - and what it's about - become increasingly important, above and beyond what it looks like. At 10zebra we believe this means engaging meaningfully with actors, values-based brands, fans and community members.
So, on to the next step: let's build an ecosystem where we can reliably pay creators to contribute performances, while protecting their likeness from being abused by contextual use outside the project. Ultimately this will come down to contracts with production companies (our clients), but we are going to try to pave the path for scenarios that work for everyone, from talent to brand.
Curious about the experience of a participant? If you want to log in, you can try.
Scan to record on your phone. (Or click if you are on it already)
%2C%20Color%3DNegative.svg){kind=icon}
