SL-03 / Iconic Sequences
The Steps
A crowd descends a monumental staircase. Montage was invented here.
The brief
Build a montage of a crowd flooding down a vast stone staircase, cutting between the mass and the individual: wide geometry of bodies, then a single face, then boots, then the whole descent again. The cut is the point — rhythm creates the tension, not the action.
The source sequence
Study the technique, not the copy. Rebuild the blocking, the lens, the movement and the rhythm — not the performances.
Watch the sequence
Embedded via youtube-nocookie.com — YouTube sets no tracking cookies until you press play.
Why it's hard
Crowds are where generative video falls apart: bodies merge, limbs get shared, people walk through each other. Sustaining a coherent crowd across multiple cuts, on a staircase, in period costume, is about as hard as it gets today.
Skill Tests
06 / 28Every challenge is scored against the same vocabulary, so you can compare them. Lit cells are what this one tests.
Success criteria
- No merged bodies, shared limbs, or people passing through each other.
- The staircase keeps consistent geometry and direction across every cut.
- Scale reads: the wide shots feel monumental against the close-ups.
Starter prompt
Built with the CEMI MediaMax system for Google Veo 3.1. Prompts stay in English — that is the language these models take instructions in. Treat it as a starting point and start varying it.
A monumental granite harbour staircase, over a hundred steps, 1905, hard midday sun. Hundreds of civilians in long coats and headscarves pour downward in one current; boots strike stone unevenly, a lost hat is trampled, dust lifts off the risers. Cut on rhythm between three scales: an extreme wide from the head of the stairs where the crowd reads as a single flowing mass; a hip-height wide-angle inside the crowd, coat wool brushing the lens as dirty foreground; a hard low angle at step level as a loose handcart bounces down riser by riser toward camera. Register of Sergei Eisenstein and DP Eduard Tisse: orthochromatic black and white, blown white sky, sooty blacks, hand-cranked 18fps with slight speed unevenness, visible emulsion grain and one or two scratches. Uncoated vintage glass. No dialogue — the cutting rhythm carries the meaning.
Style reference: Sergei Eisenstein (dir.) / Eduard Tisse (DP), 1925 montage of scale contrast
Montage is an editing idea, so the prompt is written as three deliberately mismatched scales that only mean something in sequence — that contrast, not any single frame, is the lesson. Orthochromatic stock with blown skies and hand-cranked speed unevenness is the period's real material texture and it doubles as an anti-AI move: nothing here can be rendered as clean modern digital. Vary the ratio of wide to low-angle; more low angle makes it brutal, more wide makes it tragic.
Veo will render one continuous smooth crowd shot in modern greyscale with clean digital blacks; if you see no scale jump and no grain, generate each of the three scales as a separate clip and assemble them yourself — the montage is your job, not the model's.
Ran a challenge? Show us what you got.
Share your attempt — the triumphs and the glorious failures. The most instructive entries get featured on the board.