Checklist the per-video bar — engine/sim
86.6/100
quantitative quality · weights learn from your reviews (
engine.sim.memory review social-W27-Thu-4 good|bad)⚠ 3 flag(s) — not yet ship-ready: copy_genericdup_sequence_across_assetsdup_set_across_assets · see docs/strategy/VIDEO-CHECKLIST.md
Composition comp · template family · expected output
9:16 Reelpending1:1 Squarepending16:9 Widepending9:16 4Kpending1:1 4Kpending16:9 4KpendingGIF (SMS)pending
render pending — silent master not yet on disk
expected output: 0/7 rendered — same matrix the /media preview surfaces for this asset.
Composition layer × scene 9 scenes · 69.0s · comp_id + rendered still + tier + the script
| # | Layer (comp_id · still · tier) | Beat | Timecode | Motion | Logo | Audio | VO / on-screen / caption |
|---|---|---|---|---|---|---|---|
| 1 |  matches intent shared field signature-3d | open | 0–7.7s | spatial-parallax | icon·liquid-chrome | ♪ bed_in | Building an AR filter used to need a small studio, a 3D artist, and a month nobody had to spare. on-screen: AR filters took a studio |
expected on screen: red ground · cone hero in the shared Signal Field · Augur leads · node-graph · spatial-parallax · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual node-graphshape coneground redtreatment liquid-chromemotion spatial-parallaxpower summoninstrument summon→AR filters took a studio | |||||||
| 2 |  matches intent shared field signature-3d | hook | 7.7–15.4s | kinetic-build | icon·white-knockout | ♪ node_lock | Now you describe the effect in words and a model drafts the 3D asset, so the bottleneck moved to taste. on-screen: Now you describe it |
expected on screen: red ground · cone hero in the shared Signal Field · Augur leads · mark · kinetic-build · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual markshape coneground redtreatment white-knockoutmotion kinetic-buildpower laser-lockinstrument laser-trace→Now you describe it | |||||||
| 3 |  matches intent NumberedList template | teach | 15.4–24.200000000000003s | kinetic-build | icon·liquid-chrome | ♪ node_lock | Ask a model for the object you need, drop it into the filter tool, and pin it to the face or the floor. on-screen: Generate the asset, then place it |
expected on screen: red ground · a NumberedList panel over a dimmed Signal Field · Augur leads · node-graph · kinetic-build · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id NumberedListvisual node-graphshape coneground redtreatment liquid-chromemotion kinetic-buildpower morphinstrument morph+laser→Generate the asset, then place itcurate items, nodes | |||||||
| 4 |  matches intent RankList template | proof | 24.2–32.3s | receipts-count | icon·white-knockout | ♪ node_lock | The useful ones track a real surface, so glasses sit on your nose and stay there when you turn your head. on-screen: Try-on that tracks your face |
expected on screen: red ground · a RankList panel over a dimmed Signal Field · Augur leads · receipts · receipts-count · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id RankListvisual receiptsshape coneground redtreatment white-knockoutmotion receipts-countpower receiptsinstrument spotlight→Try-on that tracks your facecurate rows, statsLabels | |||||||
| 5 |  matches intent JsonDiff template | diff | 32.3–40.4s | crossfade-8f | icon·liquid-chrome | ♪ node_lock | A goofy face filter is a toy. The same tech that lets you try the lipstick on is a sales floor. on-screen: A toy that sells isn't a toy |
expected on screen: red ground · a JsonDiff panel over a dimmed Signal Field · Augur leads · code · crossfade-8f · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id JsonDiffvisual codeshape coneground redtreatment liquid-chromemotion crossfade-8fpower morphinstrument morph→A toy that sells isn't a toycurate codeLines, fileName, lines | |||||||
| 6 |  matches intent ChecklistCard template | teach | 40.4–48.1s | kinetic-build | icon·white-knockout | ♪ node_lock | Have the model spin every color and size as a separate asset, so the buyer flips through the whole shelf. on-screen: Let AI swap the variants fast |
expected on screen: red ground · a ChecklistCard panel over a dimmed Signal Field · Augur leads · node-graph · kinetic-build · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id ChecklistCardvisual node-graphshape coneground redtreatment white-knockoutmotion kinetic-buildpower morphinstrument morph+laser→Let AI swap the variants fastcurate items, nodes | |||||||
| 7 |  matches intent StatScoreboard template | proof | 48.1–55.4s | receipts-count | icon·liquid-chrome | ♪ node_lock | People who see a product on their own face buy more and return less, because the guesswork is gone. on-screen: See it on you, then check out |
expected on screen: red ground · a StatScoreboard panel over a dimmed Signal Field · Augur leads · receipts · receipts-count · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id StatScoreboardvisual receiptsshape coneground redtreatment liquid-chromemotion receipts-countpower receiptsinstrument spotlight→See it on you, then check outcurate pillar, stats, statsLabels | |||||||
| 8 |  matches intent ListCard template | step | 55.4–62.699999999999996s | kinetic-build | icon·white-knockout | ♪ node_lock | So the move is describe the asset, track a real surface, vary the options, and tie it to checkout. on-screen: Step: describe, track, vary, sell |
expected on screen: red ground · a ListCard panel over a dimmed Signal Field · Augur leads · pipeline · kinetic-build · icon·white-knockout logo · caption bottom-left spec (the prompt): comp_id ListCardvisual pipelineshape coneground redtreatment white-knockoutmotion kinetic-buildpower throwinstrument laser-trace→Step: describe, track, vary, sellcurate items, stages, steps | |||||||
| 9 |  matches intent shared field signature-3d | resolve | 62.7–69.0s | coalescence | icon·liquid-chrome | ♪ bed_out | From a studio month to one afternoon. The Big T-M builds AR try-on that actually sells. on-screen: From studio month to one afternoon |
expected on screen: red ground · cone hero in the shared Signal Field · Augur leads · coalescence · coalescence · icon·liquid-chrome logo · caption bottom-left spec (the prompt): comp_id shared Signal Fieldvisual coalescenceshape coneground redtreatment liquid-chromemotion coalescencepower coalescenceinstrument coalescence→From studio month to one afternoon | |||||||
Format stack 3 aspects · same scenes[], re-cropped
9:16
1080×1920
Stories · TikTok · YouTube Shorts · Reels
1:1
1080×1080
LinkedIn · Facebook · Instagram
16:9
1920×1080
X/Twitter · YouTube · LinkedIn video
Channels 9 destinations
LinkedInX/TwitterYouTubeInstagramFacebookThreadsTikTokPinterestBluesky
Social captions supplemental published copy · per channel (comp_id level)
tiktokBuild an AR try-on in an afternoon (AI-assisted). Filters used to need a studio and a 3D artist for a month. Now you describe the effect and a model drafts the 3D asset. Pin it to a real surface so glasses sit on your nose when you turn your head. Spin every color as its own asset, tie it to checkout. People who see it on their face buy more, return less.
instagramAR try-on, in an afternoon.
Describe it, AI drafts the 3D asset.
Track a real surface, not the air.
Spin every color and size.
See it on you, then check out.
#augmentedreality #artryон #virtualtryon #retailtech #ecommerce
linkedinBuilding an AR filter used to need a small studio, a 3D artist, and a month nobody had to spare. Now you describe the effect in words and a model drafts the 3D asset, so the bottleneck has moved from production to taste.
What makes it sell, not just amuse:
1. Track a real surface. Glasses should sit on the nose and stay there when the head turns; that's the difference between a toy and a tool.
2. Vary the options. Have the model spin every color and size as a separate asset so the buyer can flip through the whole shelf.
3. Tie it to checkout. People who see a product on their own face buy more and return less, because the guesswork is gone.
From a studio month to one afternoon. AI-assisted and disclosed.
xAR try-on used to need a studio and a month. Now you describe the effect, a model drafts the 3D asset, you track a real surface, and tie it to checkout. People who see it on their face buy more, return less. temerarii.com
facebookBuilding an AR filter used to need a studio, a 3D artist, and a month. Now you describe the effect and a model drafts the 3D asset. The useful ones track a real surface, so glasses sit on your nose and stay there when you turn your head. Spin every color and size as its own asset, and tie it to checkout. People who see a product on their own face buy more and return less. More at temerarii.com.
threadsAR try-on used to need a studio and a month. Now you describe the effect, a model drafts the 3D asset, you track a real surface, and tie it to checkout. People who see it on their face buy more, return less.
pinterestBuild an AR try-on fast: describe the effect so AI drafts the 3D asset, track a real surface so it stays put, vary every color and size, and connect it to checkout. An evergreen guide to virtual try-on that drives sales and cuts returns.
blueskyAR try-on used to need a studio and a month. Now you describe the effect, a model drafts the 3D asset, you track a real surface, and tie it to checkout. See it on your face, buy more, return less. temerarii.com
youtubeBuild an AR Try-On in an Afternoon: Describe It, Track a Surface, Tie It to Checkout
Building an AR filter used to need a small studio, a 3D artist, and a month nobody had. Now you describe the effect in words and a model drafts the 3D asset, so the bottleneck moved to taste. This covers what makes it sell instead of just amuse: track a real surface so glasses sit on the nose and stay there, spin every color and size as a separate asset, and tie it to checkout. People who see a product on their own face buy more and return less. AI-assisted and disclosed. More at temerarii.com.