Scenario Formats
Overview
Format adaptation is derivation, not regeneration: re-prompting the concept per placement makes five
cousins, not five formats of one approved master. The failure modes are picking the wrong operation
(a resize where canvas needed inventing, a crop that beheads the subject) and deriving in the wrong
order. The canvas tools' exact contracts live in scenario-image-editing; this skill is the
decision ladder and the order of operations around them, with per-placement ratios, pixel targets,
and safe zones in references/placement-specs.md. A video master
climbs the same ladder: video resize versus generative reframe lives in scenario-video-editing,
and far ratios recompose per scenario-video. Connection and the core loop: see the scenario
skill. Lettering per format: scenario-text-overlay. 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.
The decision ladder
Per target format, take the first rung that fits. Each rung is a model_run on a model found with
search (target="models", public=true), never a dedicated MCP tool of its own:
| The target needs |
Operation |
| Same ratio, other pixels |
Resize: exact, scales pixels, invents nothing |
| A tighter ratio, edges expendable |
Resize with fit: "cover": exact, center-crops the overflow; only when the subject clears the cut |
| More canvas, composition intact |
Expand or uncrop: exact pixels, fills outward |
| Another ratio, recomposed around the subject |
Generative reframe; the text-protecting variant when lettering or marks are on the plate |
| A far ratio or a new visual hierarchy |
Recompose natively: a fresh run per scenario-image with the master as reference (scenario-consistency), composed for that ratio |
The last rung applies more often than it looks: 16:9 key art seldom survives to 9:16 by any amount
of outpainting, which is why the director siblings (scenario-video-ads) design each delivery ratio
as its own composition.
Order of operations
- Approve one master first, at the largest clean size available, on a text-free plate (unattended,
the task's named master or the brief's own description stands in for the approval).
- Derive every format from that master, never from another derivative: derivative-of-derivative
compounds re-rendering artifacts.
- Reframe and expand before grading and grain: generative canvas work re-renders the image, so
finishing passes applied first come back partly reinterpreted (
scenario-image-editing holds the
pipeline order). A video reframe also precedes any upscale: it renders at its own resolution tier
whatever the input carries (1080p at most at authoring time), so an upscale ahead of it is
discarded; upscale the reframed clip to delivery size.
- Verify by measurement before finishing: reframe ratio enums are approximate (a 4:5 request came
back 29:36 at authoring time), so check output dimensions, land exact with a resize, and
batch-check that subjects survived with
asset_analyze (scenario-asset-analysis).
- Letter last: re-overlay lettering per format with
scenario-text-overlay, sized to each final
canvas, since type scaled by a resize turns soft and each placement has its own safe area. Keep
critical content and text away from the edges platform UI covers: each placement's target and
safe zone is in references/placement-specs.md as an
authoring-time value, so confirm contractual specs with the user (unattended, task instructions
win over the reference, and the delivery report states which was used).
Worked example: key art to story, feed, and thumbnail
- Master: 16:9 text-free key art, approved.
- 1:1 feed: generative reframe with a prompt naming what must stay ("the knight centered, both
banners visible"), then a resize pass to the exact deliverable pixels.
- 9:16 story: a far ratio, so recompose natively: one run per
scenario-image with the master as
reference and a 9:16 composition clause; the master holds palette and subject on-look.
- Thumbnail: readability rules the crop, so reframe tight on the face or product, land exact with a
resize, then
asset_display the result and judge it small: thumbnails are seen at a tenth of
their size.
- Verify dimensions against the deliverable list and batch-check that subjects survived with one
asset_analyze pass, then overlay the title card per format onto each final canvas and file the
set in a collection.
Common mistakes
- Re-prompting per format: five generations of one prompt are five different images; derive from the
master.
- Stretching into a new ratio with a resize (
fit: "stretch"): it distorts. A ratio change is
fit: "cover" when the edges are expendable, else reframe, expand, or recomposition.
- Grading and grain before reframing: the order is reshape, then grade, then texture.
- Deriving from the lettered master: generative operations re-render type; keep a text-free plate
and re-overlay per format.
- Trusting a ratio enum: measure the output and resize to exact.
- Center-cropping toward 9:16 because it is cheap: it is also how subjects lose their heads; the
ladder exists to be climbed.
- Skipping
dry_run on reframes: generative canvas work is the expensive step in the chain, tens of
times an effect's price (scenario-image-editing).
1---2name: scenario-formats3description: "Use when one approved visual, image or video, must ship at many sizes or placements through Scenario: adapting a master to 1:1, 4:5, 9:16, or 16:9, social formats for feeds and stories, YouTube thumbnails, storefront capsules and app store graphics, marketplace product images, link previews, display banners, a website hero, or choosing between crop, resize, expand, and generative reframe. Keywords: aspect ratio, resize, reframe, outpaint, expand, derivative, safe zone, thumbnail, banner."4license: MIT5metadata:6 source: https://skillmd.com/skills/scenario-labs/scenario-formats7---89# Scenario Formats1011## Overview1213Format adaptation is derivation, not regeneration: re-prompting the concept per placement makes five14cousins, not five formats of one approved master. The failure modes are picking the wrong operation15(a resize where canvas needed inventing, a crop that beheads the subject) and deriving in the wrong16order. The canvas tools' exact contracts live in `scenario-image-editing`; this skill is the17decision ladder and the order of operations around them, with per-placement ratios, pixel targets,18and safe zones in [references/placement-specs.md](references/placement-specs.md). A video master19climbs the same ladder: video resize versus generative reframe lives in `scenario-video-editing`,20and far ratios recompose per `scenario-video`. Connection and the core loop: see the `scenario`21skill. Lettering per format: `scenario-text-overlay`. If a sibling skill named here is missing from22your available skills, load it with `skill_get` (Scenario MCP) or ask the user to install it23(https://github.com/scenario-labs/skills#install); unattended, proceed from tool schemas and flag24the gap.2526## The decision ladder2728Per target format, take the first rung that fits. Each rung is a `model_run` on a model found with29`search` (`target="models"`, `public=true`), never a dedicated MCP tool of its own:3031| The target needs | Operation |32| -------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------- |33| Same ratio, other pixels | Resize: exact, scales pixels, invents nothing |34| A tighter ratio, edges expendable | Resize with `fit: "cover"`: exact, center-crops the overflow; only when the subject clears the cut |35| More canvas, composition intact | Expand or uncrop: exact pixels, fills outward |36| Another ratio, recomposed around the subject | Generative reframe; the text-protecting variant when lettering or marks are on the plate |37| A far ratio or a new visual hierarchy | Recompose natively: a fresh run per `scenario-image` with the master as reference (`scenario-consistency`), composed for that ratio |3839The last rung applies more often than it looks: 16:9 key art seldom survives to 9:16 by any amount40of outpainting, which is why the director siblings (`scenario-video-ads`) design each delivery ratio41as its own composition.4243## Order of operations44451. Approve one master first, at the largest clean size available, on a text-free plate (unattended,46 the task's named master or the brief's own description stands in for the approval).472. Derive every format from that master, never from another derivative: derivative-of-derivative48 compounds re-rendering artifacts.493. Reframe and expand before grading and grain: generative canvas work re-renders the image, so50 finishing passes applied first come back partly reinterpreted (`scenario-image-editing` holds the51 pipeline order). A video reframe also precedes any upscale: it renders at its own resolution tier52 whatever the input carries (1080p at most at authoring time), so an upscale ahead of it is53 discarded; upscale the reframed clip to delivery size.544. Verify by measurement before finishing: reframe ratio enums are approximate (a 4:5 request came55 back 29:36 at authoring time), so check output dimensions, land exact with a resize, and56 batch-check that subjects survived with `asset_analyze` (`scenario-asset-analysis`).575. Letter last: re-overlay lettering per format with `scenario-text-overlay`, sized to each final58 canvas, since type scaled by a resize turns soft and each placement has its own safe area. Keep59 critical content and text away from the edges platform UI covers: each placement's target and60 safe zone is in [references/placement-specs.md](references/placement-specs.md) as an61 authoring-time value, so confirm contractual specs with the user (unattended, task instructions62 win over the reference, and the delivery report states which was used).6364## Worked example: key art to story, feed, and thumbnail65661. Master: 16:9 text-free key art, approved.672. 1:1 feed: generative reframe with a prompt naming what must stay ("the knight centered, both68 banners visible"), then a resize pass to the exact deliverable pixels.693. 9:16 story: a far ratio, so recompose natively: one run per `scenario-image` with the master as70 reference and a 9:16 composition clause; the master holds palette and subject on-look.714. Thumbnail: readability rules the crop, so reframe tight on the face or product, land exact with a72 resize, then `asset_display` the result and judge it small: thumbnails are seen at a tenth of73 their size.745. Verify dimensions against the deliverable list and batch-check that subjects survived with one75 `asset_analyze` pass, then overlay the title card per format onto each final canvas and file the76 set in a collection.7778## Common mistakes7980- Re-prompting per format: five generations of one prompt are five different images; derive from the81 master.82- Stretching into a new ratio with a resize (`fit: "stretch"`): it distorts. A ratio change is83 `fit: "cover"` when the edges are expendable, else reframe, expand, or recomposition.84- Grading and grain before reframing: the order is reshape, then grade, then texture.85- Deriving from the lettered master: generative operations re-render type; keep a text-free plate86 and re-overlay per format.87- Trusting a ratio enum: measure the output and resize to exact.88- Center-cropping toward 9:16 because it is cheap: it is also how subjects lose their heads; the89 ladder exists to be climbed.90- Skipping `dry_run` on reframes: generative canvas work is the expensive step in the chain, tens of91 times an effect's price (`scenario-image-editing`).