Scenario Fan Cam
Overview
A fan cam is a two-stage build: an identity-preserving image edit places the person into a 16:9
broadcast still, and image-to-video animates the approved still into a reaction. The uploaded photo
is an identity reference, never a start frame: feeding it straight to a video model animates a
portrait, not a broadcast. Stage one is cheap and stage two is not, so the still carries every
decision worth approving.
Use only photos of the user or of people who gave them permission; refuse celebrity or stranger
insertions. Real faces also trip provider filters more than most subjects: on a block, see
scenario-moderation. Connection and the core loop: see the scenario skill in this repo. If a
sibling skill named here is missing from your available skills, load it with skill_get (Scenario
MCP) or ask the user to install it (https://github.com/scenario-labs/skills#install); unattended,
proceed from tool schemas and flag the gap.
Quick reference
Discover members with recommend, passing the stage's capability and the user's own words: it ranks
by measured cost and latency and names the purpose-built pick, where a capability-worded search
returns hundreds of keyword hits with nothing to choose between them. Read next_step before taking
a pick, per the scenario skill. Keep search for a member you can already name. Never assert a
generative model's id as a constant. Scenario's own single-purpose tool models are named outright
below: there is exactly one of each, so discovering them would only re-derive a constant.
| Stage |
What happens |
Detail |
| 1. Identity still |
Image-edit member (img2img) composites the person into a 16:9 crowd frame |
scenario-image, scenario-consistency |
| 2. Still gate |
Likeness checked against the photo before any video money is spent |
scenario-asset-analysis |
| 3. Animate |
Image-to-video from the approved still, reaction beats, one camera move |
scenario-kling, scenario-video |
| 4. Identity gate |
Frames extracted from the clip, compared to the approved still |
scenario-asset-analysis |
| 5. Overlays |
Score strip, channel bug, lower third composited as post layers, never generated |
scenario-text-overlay, scenario-video-assembly |
| 6. Derivatives |
9:16 and 1:1 social cuts off the 16:9 master |
scenario-formats |
Broadcast grammar is what sells the shot, so prompt it explicitly at both stages: long-lens
compression with the crowd defocused in front and behind, harsh stadium floodlight or arena strobe,
slight motion blur, the camera hunting and reframing as it finds the subject. Keep the person
mid-ground among other fans, off-center, at broadcast camera height. A centered, well-lit, eye-level
subject reads as a photoshoot in a stadium, not a cutaway.
Give the reaction an arc rather than a state: oblivious, then noticing the camera or the screen,
then the reaction the user asked for (cheering, laughing, disbelief, heartbreak). Multi-beat
prompting per the video family's contract keeps the turn inside one clip.
Worked example: caught on the stadium screen, 8 seconds
- Collect the photo, the sport or event, venue mood, wardrobe, and the wanted reaction.
upload_asset the photo once and reuse the returned asset id.
- Create this run's collection before the first generation (
collection_create, catalog write
lane, name only), then collection_add_assets each keeper as it lands; its returned
itemCount is the receipt.
recommend with capability="img2img" and the placement described in words; prefer a ranked
entry that takes several reference images, and read model_schema_get for those inputs
(scenario-image for the lane, scenario-consistency for reference discipline).
- Edit prompt: "the person from the reference image seated mid-crowd at a floodlit football
stadium, 16:9 television cutaway, long-lens crowd compression, no text, logos, or graphics in
frame". Keep the plate text-free: overlays come later.
- Gate the still:
asset_display it for approval, and inventory the likeness features that must
hold (face geometry, hairline, skin tone, wardrobe) with the analysis lane from
scenario-asset-analysis; a change in any inventoried feature fails. Unattended, that inventory
stands in for the user's sign-off.
recommend with capability="img2video" and the reaction described in words, then check the
pick against scenario-kling or scenario-video. The brief's length filters members: duration
is usually a fixed enum a member either reaches or does not, and the tiers that reach it sit far
apart on price, so model_schema_get each candidate and compare with model_run dry_run=true.
- Run with the approved still as the start image and two beats: "she chats, unaware" then "she
spots herself on the stadium screen, stands, and cheers", one slow reframing move,
wait=false,
then jobs_wait re-called with pending_job_ids on timeout, never a second model_run.
- Check the clip against the approved still on frames the platform produced: the free
firstFrame
and lastFrame off asset_get first, then model_scenario-video-to-image-seq for a mid-clip
frame (a tool-model lane per scenario-video-editing). A local extraction is not a substitute at
any budget, because it yields no asset to file or audit and the gate stops being traceable. A
change in any inventoried feature fails the clip, and so does legible generated type: ribbon
boards and jumbotron glyphs creep in even against a no-text prompt, worst late in the clip. The
retry starts from the same still, never from the drifted output.
- Assemble on-platform with
model_scenario-compose-video (a tool-model lane per
scenario-video-assembly), layering the score strip and channel bug from scenario-text-overlay
in the safe corners; a local editor is the wrong lane. Give every overlay layer an explicit
width and height, since leaving them empty is documented as native size and does not hold,
and pin durationMode: "custom" to the clip's length, since an image layer otherwise stretches
the composition past it. A succeeded compose job is not proof the layers drew: pull a frame from
the composite (the free firstFrame) and confirm every layer is present and placed before
delivering. Then cut 9:16 per scenario-formats, a resize rather than a reframe, whose video
members outpaint a wider frame instead of cutting one. Its cover mode crops from the center, so
when the subject sits off-center put the master on a 9:16 compositor canvas positioned to hold
them instead. asset_display both.
Common mistakes
- Animating the uploaded photo directly: the mandatory stage is the broadcast still; skip it only
when the user hands over an already approved 16:9 frame.
- Letting the image or video model render the scoreboard, channel bug, or jersey sponsor text:
generated type drifts frame to frame; composite graphics in post on a text-free plate.
- Portrait staging: centered subject, flattering light, and empty seats around them break the
documentary read; bury them in a reacting crowd.
- Judging likeness from one glance at the moving clip: drift hides between glances; run the
frame-extract gate.
- Retrying from a drifted clip instead of the approved still: errors compound.
- Composing the master at 9:16: broadcast is 16:9; verticals are derivatives.
- A flat emotional state for the whole clip: without the notice-then-react turn, the result is a
looping portrait, not a fan cam.
- Compound camera moves: one reframing drift; the crowd and the reaction supply the motion.
1---2name: scenario-fan-cam3description: "Use when putting a person from a photo into live-broadcast crowd footage with Scenario: a stadium or arena fan-cam reaction, a jumbotron or kiss-cam moment, a spectator cutaway at a match or concert, a courtside or front-row sighting, or a personalized sports-TV still that then animates into video. Keywords: fan cam, crowd reaction, jumbotron, stadium screen, kiss cam, broadcast cutaway, spectator, crowd shot, sports TV, courtside, arena."4license: MIT5metadata:6 source: https://skillmd.com/skills/scenario-labs/scenario-fan-cam7---89# Scenario Fan Cam1011## Overview1213A fan cam is a two-stage build: an identity-preserving image edit places the person into a 16:914broadcast still, and image-to-video animates the approved still into a reaction. The uploaded photo15is an identity reference, never a start frame: feeding it straight to a video model animates a16portrait, not a broadcast. Stage one is cheap and stage two is not, so the still carries every17decision worth approving.1819Use only photos of the user or of people who gave them permission; refuse celebrity or stranger20insertions. Real faces also trip provider filters more than most subjects: on a block, see21`scenario-moderation`. Connection and the core loop: see the `scenario` skill in this repo. If a22sibling skill named here is missing from your available skills, load it with `skill_get` (Scenario23MCP) or ask the user to install it (https://github.com/scenario-labs/skills#install); unattended,24proceed from tool schemas and flag the gap.2526## Quick reference2728Discover members with `recommend`, passing the stage's capability and the user's own words: it ranks29by measured cost and latency and names the purpose-built pick, where a capability-worded `search`30returns hundreds of keyword hits with nothing to choose between them. Read `next_step` before taking31a pick, per the `scenario` skill. Keep `search` for a member you can already name. Never assert a32generative model's id as a constant. Scenario's own single-purpose tool models are named outright33below: there is exactly one of each, so discovering them would only re-derive a constant.3435| Stage | What happens | Detail |36| ----------------- | -------------------------------------------------------------------------------- | -------------------------------------------------- |37| 1. Identity still | Image-edit member (`img2img`) composites the person into a 16:9 crowd frame | `scenario-image`, `scenario-consistency` |38| 2. Still gate | Likeness checked against the photo before any video money is spent | `scenario-asset-analysis` |39| 3. Animate | Image-to-video from the approved still, reaction beats, one camera move | `scenario-kling`, `scenario-video` |40| 4. Identity gate | Frames extracted from the clip, compared to the approved still | `scenario-asset-analysis` |41| 5. Overlays | Score strip, channel bug, lower third composited as post layers, never generated | `scenario-text-overlay`, `scenario-video-assembly` |42| 6. Derivatives | 9:16 and 1:1 social cuts off the 16:9 master | `scenario-formats` |4344Broadcast grammar is what sells the shot, so prompt it explicitly at both stages: long-lens45compression with the crowd defocused in front and behind, harsh stadium floodlight or arena strobe,46slight motion blur, the camera hunting and reframing as it finds the subject. Keep the person47mid-ground among other fans, off-center, at broadcast camera height. A centered, well-lit, eye-level48subject reads as a photoshoot in a stadium, not a cutaway.4950Give the reaction an arc rather than a state: oblivious, then noticing the camera or the screen,51then the reaction the user asked for (cheering, laughing, disbelief, heartbreak). Multi-beat52prompting per the video family's contract keeps the turn inside one clip.5354## Worked example: caught on the stadium screen, 8 seconds55561. Collect the photo, the sport or event, venue mood, wardrobe, and the wanted reaction.57 `upload_asset` the photo once and reuse the returned asset id.582. Create this run's collection before the first generation (`collection_create`, catalog write59 lane, `name` only), then `collection_add_assets` each keeper as it lands; its returned60 `itemCount` is the receipt.613. `recommend` with `capability="img2img"` and the placement described in words; prefer a ranked62 entry that takes several reference images, and read `model_schema_get` for those inputs63 (`scenario-image` for the lane, `scenario-consistency` for reference discipline).644. Edit prompt: "the person from the reference image seated mid-crowd at a floodlit football65 stadium, 16:9 television cutaway, long-lens crowd compression, no text, logos, or graphics in66 frame". Keep the plate text-free: overlays come later.675. Gate the still: `asset_display` it for approval, and inventory the likeness features that must68 hold (face geometry, hairline, skin tone, wardrobe) with the analysis lane from69 `scenario-asset-analysis`; a change in any inventoried feature fails. Unattended, that inventory70 stands in for the user's sign-off.716. `recommend` with `capability="img2video"` and the reaction described in words, then check the72 pick against `scenario-kling` or `scenario-video`. The brief's length filters members: `duration`73 is usually a fixed enum a member either reaches or does not, and the tiers that reach it sit far74 apart on price, so `model_schema_get` each candidate and compare with `model_run` `dry_run=true`.757. Run with the approved still as the start image and two beats: "she chats, unaware" then "she76 spots herself on the stadium screen, stands, and cheers", one slow reframing move, `wait=false`,77 then `jobs_wait` re-called with `pending_job_ids` on timeout, never a second `model_run`.788. Check the clip against the approved still on frames the platform produced: the free `firstFrame`79 and `lastFrame` off `asset_get` first, then `model_scenario-video-to-image-seq` for a mid-clip80 frame (a tool-model lane per `scenario-video-editing`). A local extraction is not a substitute at81 any budget, because it yields no asset to file or audit and the gate stops being traceable. A82 change in any inventoried feature fails the clip, and so does legible generated type: ribbon83 boards and jumbotron glyphs creep in even against a no-text prompt, worst late in the clip. The84 retry starts from the same still, never from the drifted output.859. Assemble on-platform with `model_scenario-compose-video` (a tool-model lane per86 `scenario-video-assembly`), layering the score strip and channel bug from `scenario-text-overlay`87 in the safe corners; a local editor is the wrong lane. Give every overlay layer an explicit88 `width` and `height`, since leaving them empty is documented as native size and does not hold,89 and pin `durationMode: "custom"` to the clip's length, since an image layer otherwise stretches90 the composition past it. A succeeded compose job is not proof the layers drew: pull a frame from91 the composite (the free `firstFrame`) and confirm every layer is present and placed before92 delivering. Then cut 9:16 per `scenario-formats`, a resize rather than a reframe, whose video93 members outpaint a wider frame instead of cutting one. Its `cover` mode crops from the center, so94 when the subject sits off-center put the master on a 9:16 compositor canvas positioned to hold95 them instead. `asset_display` both.9697## Common mistakes9899- Animating the uploaded photo directly: the mandatory stage is the broadcast still; skip it only100 when the user hands over an already approved 16:9 frame.101- Letting the image or video model render the scoreboard, channel bug, or jersey sponsor text:102 generated type drifts frame to frame; composite graphics in post on a text-free plate.103- Portrait staging: centered subject, flattering light, and empty seats around them break the104 documentary read; bury them in a reacting crowd.105- Judging likeness from one glance at the moving clip: drift hides between glances; run the106 frame-extract gate.107- Retrying from a drifted clip instead of the approved still: errors compound.108- Composing the master at 9:16: broadcast is 16:9; verticals are derivatives.109- A flat emotional state for the whole clip: without the notice-then-react turn, the result is a110 looping portrait, not a fan cam.111- Compound camera moves: one reframing drift; the crowd and the reaction supply the motion.