Make a ~30 s product ad that stars the brand's own mascot: a short cartoon story built on the product's name or promise, narrated, with the product's real substance (its UI, code, integrations, dashboard) composited on top as motion graphics and key-phrase captions. It works from the product's website and mascot art alone. An existing launch video, if there is one, supplies the beats, the real screens and the logos, and is what a side-by-side is measured against.
Use the brand's own materials, made for or shared by the brand owner, and keep the
result private to them until they agree to it being shown. Partner logos appear only
the way the brand already shows them (guide-capture-a-brand, Avoid). Rounds and
deliverables follow the core skill. This is a worked character-story treatment of a
conceptual product or brand film. Use it when the mascot's actions express the promise;
the steps below own this recipe's sequence.
Steps
- Break down the source (
guide-pull-product-highlights, website and launch-video routes;guide-capture-a-brandfor the look): every substantive point (what it does, setup time, languages, integrations, monitoring) insource/facts.md, each to survive into the ad in the picture, the narration or the graphics; from a launch video, also its beats and full-resolution frames of its product screens. - Concept and shot list: a story that gives the mascot a role expressing the
product's promise (
llm-pick-a-visual-metaphor); a name-based pun worked in the example, but choose the idea for this brand and audience. Use the mascot-story shape, about 7 shots of 3–5 s for 28 s (llm-write-an-ad-script). Per shot: the picture, the narration line, and the real screen or logo that goes over it. Gate: the shot list with a price, before any spend. - Voice (
guide-voice-a-script, A narrator for a short): three auditions of the whole script, so the person hears the pacing too. Gate: a pick. - Look (
guide-pick-a-stylized-look, the drawn 2D cartoon in itsreferences/looks.md, From a mascot's own art): one style frame of a key shot on nano banana Pro edit, the mascot art as reference, 2 takes, 2K, 16:9. Gate: a pick. - Stills from the picked frame plus the mascot art, 2 takes each
(
guide-pick-a-stylized-look, Process step 4). Integrations the brand lists can be drawn into the world, their logos given as references ("a sign above each stall shows the logo in the second image"), and then also appear as graphics. Remove anything the characters could walk through (ropes, rails) unless the action needs it. Gate: areview_chooseper shot, its takes as the options, all in the same turn. - Motion test, then the rest (
guide-pick-a-stylized-look, Process step 5;h3-max-image-to-videoat 1080P): the test "Static shot, locked on the opening framing". Gate: the motion. Direct exits explicitly ("turns and strolls to the right toward the open doors"). Judge each on a frame sheet by eye: raw first-frame SSIM on grainy cartoon renders reads 0.70 to 0.85 even on a correct opening. - Narration track: one file per line (
guide-voice-a-script, One take, or one file per line), since each line is placed on a shot of fixed length; transcribe each (whisper-cli-transcribe-with-word-times) for the graphics' cues. - Music (
elevenlabs-generate-music, Fit the bed to the cut): one bed whose sections land on the cut (sparse for shot 1, a groove in the middle, a final hit on the end card). - Base cut (
ffmpeg-cut-clips-to-a-voiceover, one file per line at its shot's start, the clips' own effects at about 0.35, the bed ducked). - Motion graphics over the base cut:
- key-phrase captions only, 2 to 4 words a shot, in a heavy display serif in the
brand's colours, popped on the spoken word, and the URL as the last one
(
hn4a-compositor-brand-ad-titles,key_phrase); - the product's real screens (an activation dialog, a code snippet, a dashboard)
as cards on the line that mentions them, from the launch video's frames or site
screenshots, including one that replaces something in the picture (a dashboard
on a wall screen) on that shot's cut frames (
guide-show-a-product-on-screen, the card treatment; reveal parts when it clarifies the point); - small logos (languages, integrations) popping in one by one on each name
(
hn4a-compositor-motion-graphics). Gate: the live spec (hn4a-compositor, Live spec, then render), with stills at each cue.
- key-phrase captions only, 2 to 4 words a shot, in a heavy display serif in the
brand's colours, popped on the spoken word, and the URL as the last one
(
- Deliver: render, check the frame count, transcribe the cut against the script,
measure loudness (about −17 LUFS, peaks under −1.5 dBTP; trim the gain rather than
re-normalizing). Deliver per the core skill:
deliverthe film, and with it a side-by-side when there is an original (original left, ours right, our audio). Fix notes by re-rendering only the changed span (render --frames A:B --into) on a copy of the last render.
Choices this workflow makes
- The story world expresses the product's promise
(
llm-pick-a-visual-metaphor), and the mascot gets a job in it. - Substance rides on top as the product's real screens, never generated UI: generated screens get the text wrong.
- One narration file per line, never one take cut into lines.
- Every look is gated: voice, style frame, stills, one motion test, the live layout.
- When it's a gift for the founder, draft the note for the person to send
privately with the side-by-side (
llm-draft-a-gift-video-note).
Dead ends
- A dashboard card that popped in 0.4 s into its shot: the picture underneath flashed. Cut it on the measured frame.
- A busy style frame as the only reference: about half the stills copied its set
(
guide-pick-a-stylized-look, Choosing).
Worked example
Globex, a developer tool with a drawn robot mascot, from its site and its own launch video. 16:9 1920×1080, 24 fps, 28 s, 7 shots of 3 to 5 s. The story world puns on the product's name; the mascot gets a uniform and a job in it.
| Shot | Point | Picture | Over it |
|---|---|---|---|
| 1 | The problem | The mascot at its post, a queue waiting | key phrase |
| 2 | What it does | The mascot at work | key phrase, the product's code snippet card |
| 3 | Setup time | A quick install | the activation dialog card |
| 4 | Languages | Visitors from many places | language logos, one per spoken name |
| 5 | Integrations | Stalls with the partners' logos drawn in | integration logos popping on their names |
| 6 | Monitoring | A big screen in the world | the dashboard card, cut on the measured frames |
| 7 | End | The mascot waves | the URL |
Three review rounds. Round 1's main note: the "no on-screen text" cut had lost the product's points, so key-phrase captions and the real screens went on top. The person also heard an artifact where one narration take had been cut into lines (fixed by voicing each line on its own) and saw the picture flash under the dashboard card (fixed by cutting it on the measured frames). It was approved beside the side-by-side.
Spend at 1080P: stills about $3, video about $6, voice and music under $0.50: about $10.


