← Selected workCrocs / Spec campaign · 2026

CrocsFrom a brief to two finished campaigns.

Two complete :15 spec campaigns, fourteen final frames and two films, produced solo through an AI-assisted pipeline under human art direction. Stills and motion generated through APIs, beat-cut in code with Remotion.

Pink Crocs on grass beside a running sprinkler, shot top-down Character in a denim outfit with navy Crocs Sand-dusted Crocs on a beach, shot top-down Character in a color-block windbreaker with loaded green Crocs Crocs on a kitchen floor, shot top-down

01 / The brief

Could one person take a brand brief to finished campaigns?

The test: study a real brand’s tone, product line, and visual language, then deliver two distinct, finished social campaigns using current image and video models, with every creative decision made by a human art director.

The hard part of AI production is not generating images. It is consistency: the same camera, the same product colorways, the same character, frame after frame, until nine separate generations read as one campaign. That is a discipline problem, not a prompting problem.

The bar for every frame

“It has to pass as real, or it doesn’t ship.”
  • Nano Banana Pro
  • Seedance 2.0
  • fal.ai
  • Remotion
A

Project A

“Every you. Every day.”

One fixed top-down camera. Feet in Crocs, dead center, every frame. Everything else changes. Nine ordinary moments from one life, beat-cut into a :15 loop. The locked composition is what makes nine generations read as one campaign.

9Frames
124BPM cut
1Camera
:15 filmProject A
Frame 1, the sprinkler: pink Crocs on grass, shot top-down
Frame 01 / The composition lockEvery other frame anchors to this camera, scale, and stance.
Six-panel character sheet establishing one face, hair, and build from several angles
Character canonIdentity locked once on mid-gray seamless, then carried through ten stills and five clips.
B

Project B

Fashion swap.

One character, one fixed frame, five looks. The Crocs change with every outfit. Hard cuts land mid-gesture, and the styling coordination is the content. Character consistency held across every still and clip from a single locked face reference.

5Looks
10Stills
1Face reference
:15 filmProject B

02 / Six stages

Every select human-approved.
01 / Brief

Brief

Brand study from the live platform. Tone pillars and a hard avoid-list set before any generation.

02 / Refs

Refs

A product reference library from catalog photography, colorways checked at the pixel level.

03 / Lock

Lock

One hero frame iterated to approval, then locked as the composition reference for every frame after it.

04 / Stills

Stills

Generated against the locks and checked at zoom per select. Anything that does not pass as real is cut.

05 / Motion

Motion

Micro-motion keeps subjects still while environments move. Identity refs ride along on every clip.

06 / Edit

Edit

Cut grids built in code from each track’s measured BPM. One global grade across every select.

Composition lockOne hero frame became law for all nine.

The approved frame-one image was attached to every later generation as a composition reference. Camera angle, product scale, and stance had to match it exactly. When a graphic ground kept pulling the pose, the lock won.

Character canonIdentity locked once, then defended.

Project B’s character came from a single face reference shot on mid-gray seamless, because white backdrops bleed into final lighting and push skin toward plastic. Any marker that drifted between looks was cut from canon rather than patched per frame.

Re-render vs. editTwo tools for two kinds of fix.

Editing models stay close to their base image: they remove elements and clean surfaces but resist repositioning. Re-render for layout changes, surgical edit for local fixes. Every select checked at full resolution, because feed-size review misses seating and mount errors.

Hard cuts onlyGenerative transitions were tested and rejected.

AI flash-swaps and morph transitions both read as AI: one felt wrong on the beat, the other hybridized mid-frame. Every cut in both films is a straight cut in the Remotion edit, with Project B’s cuts landing mid-gesture.

Motion fidelityThe canonical reference rides along on every clip.

The first motion pass showed face drift and AI skin, because image-to-video only sees the plate. The fix was reference-to-video at 1080p with the character canon attached to every generation. Upscalers sharpen what is there; they do not fix it.

03 / What this proves

Consistency is the product.

Anyone can generate a good-looking AI image. The difference between a demo and a campaign is whether frame seven matches frame one: same camera, same colorway, same charms in the same holes. That takes reference discipline, a requirement that every frame pass as real, and an art director willing to throw out good frames that do not match.

The pipeline produced two campaigns for one brand, with a full generation log behind every select. The process generalizes to any brand.

Brief to campaign

Bring a brand brief. Leave with a campaign.

Another AI production workflow

Thirteen spots. Ten brands. One pipeline.

Explore the AI Video Pipeline

Scroll to explore. Press Escape to close.