Scenario Product Shots
Overview
The product is never generated. A text-prompted bottle ships a wrong label to a landing page; every
credible shot starts from an uploaded photo of the real product, and fidelity is a gated check, not
a hope. Two lanes cover most work: deterministic packshot tools (cutout, background, shadow,
relight) and generative scene placement with an instruction-editing model. Connection and the core
loop: see the scenario skill. Edit-model contracts: scenario-image. Deterministic tools:
scenario-image-editing. Reading assets back: scenario-asset-analysis. Animating an approved
still into an ad: scenario-video-ads. 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
| Need |
Route |
| The source |
upload_asset the best photo available: sharp, evenly lit, whole product in frame (search "uncrop" finds tools that rebuild a clipped edge) |
| Fidelity checklist |
asset_analyze the upload once, instructing an inventory of label text, geometry, materials, and colors; every later check reuses it |
| Packshot |
recommend with the packshot need in the user's own words (a cutout-and-stage tool with solid, transparent, or custom backgrounds, margins, and shadows was the authoring-time hit), or background removal plus your own compose |
| Lifestyle scene |
recommend with capability="img2img", product photo as reference, preserve-first prompt, one scene per run |
| Relight |
search "relighting" (the authoring-time hit adjusts light, exposure, and mood, with a brand-color lock) |
| Upscale keepers |
recommend with the user's own words; product-tuned upscalers existed at authoring time |
| Gate |
asset_analyze the outputs against the checklist: up to 10 ids in images, the saved checklist in text_inputs, the letter-by-letter brief in instruction |
The preserve-first prompt
Scene prompts subordinate the world to the product: "The exact can from the reference image,
proportions and colors unchanged, the label reads 'SUMMIT COLD BREW', no other text, standing on a
wet slate counter, morning side light, shallow depth of field." Name the placement, the surface, the
light. What goes unstated drifts: "label unchanged" alone leaves the type to whatever the model
resolves from the reference, so the preserve clause quotes the checklist's label copy (existing
on-pack text only) and the gate reads it back letter by letter rather than trusting the render.
Shadows and reflections carry the realism: a cutout pasted without them floats. Prefer a stage tool
that rebuilds shadows, or name one in the edit prompt ("soft contact shadow falling right").
Worked example: one can, a packshot plus three scenes
upload_asset the studio photo, then upload_asset_complete: asset_can.
- Build the checklist once with
asset_analyze (write lane, contract in
scenario-asset-analysis); the inventory lands as a text asset, so asset_download it and keep
the text.
- Packshot:
recommend with the packshot need in the user's own words, model_schema_get the
pick, then run it with asset_can in its image field, the background set to the brand hex, and
margins per the marketplace's current spec (confirm specs with the user; unattended, take them
from the task instructions, else keep the tool's defaults).
- Scenes:
recommend with capability="img2img"; on next_step.type="ask_user", present the
options (unattended, the task instructions name the pick, else proceed: specialty.model_id
first, skipping a specialty whose caveats or when_general_better name the task at hand, then
the top ranked entry, never one flagged requires_plan_upgrade). model_schema_get the pick,
then three runs, each the preserve-first prompt with one scene clause and asset_can wired as
the schema says (an array only under array: true).
jobs_wait, then gate all four outputs in one asset_analyze call, the saved checklist passed
via text_inputs and an instruction to read the label back letter by letter. A drifted label
fails the shot: re-run from asset_can with the preserve clause tightened (the quoted copy
spelled letter by letter, "no other text" kept), never from the drifted output. Text the gate
cannot resolve at output resolution is unverified, not passed: upscale and re-gate, or flag it in
the delivery note.
- Upscale the keepers,
asset_download with format="png", file the set in a collection.
Common mistakes
- Generating the product from a text description because the photo seems easy to describe: the one
unfixable error, since no edit restores a label that never existed.
- Compositing from a screenshot of a crop: fidelity caps at the source; ask for the original file,
and when nobody can supply one, proceed with the best source at hand and flag the ceiling in the
delivery note.
- Skipping the gate because it "looks fine": label drift hides at thumbnail size; the checklist
compare reads letter by letter.
- Prompting prices, claims, or promo copy into the image: overlay them with
scenario-text-overlay;
regulations and locales change faster than plates.
- Removing the background and losing the real shadow with it: restage with a shadow-building tool or
prompt a new one.
- One run with a batch count for "the same scene, four angles": per-angle clauses need one run each
(
scenario-image).
1---2name: scenario-product-shots3description: "Use when producing product photography with Scenario from a real product photo: e-commerce packshots on white, transparent, or brand backgrounds, lifestyle scenes placing the product in an environment, hero shots for a landing page or marketplace listing, angle and colorway sets, relighting or shadow fixes, or any shot where the label, logo, and shape must stay exact. Keywords: product photo, packshot, e-commerce, lifestyle shot, compositing, relight, label fidelity, catalog."4license: MIT5metadata:6 source: https://skillmd.com/skills/scenario-labs/scenario-product-shots7---89# Scenario Product Shots1011## Overview1213The product is never generated. A text-prompted bottle ships a wrong label to a landing page; every14credible shot starts from an uploaded photo of the real product, and fidelity is a gated check, not15a hope. Two lanes cover most work: deterministic packshot tools (cutout, background, shadow,16relight) and generative scene placement with an instruction-editing model. Connection and the core17loop: see the `scenario` skill. Edit-model contracts: `scenario-image`. Deterministic tools:18`scenario-image-editing`. Reading assets back: `scenario-asset-analysis`. Animating an approved19still into an ad: `scenario-video-ads`. If a sibling skill named here is missing from your available20skills, load it with `skill_get` (Scenario MCP) or ask the user to install it21(https://github.com/scenario-labs/skills#install); unattended, proceed from tool schemas and flag22the gap.2324## Quick reference2526| Need | Route |27| ------------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |28| The source | `upload_asset` the best photo available: sharp, evenly lit, whole product in frame (`search` `"uncrop"` finds tools that rebuild a clipped edge) |29| Fidelity checklist | `asset_analyze` the upload once, instructing an inventory of label text, geometry, materials, and colors; every later check reuses it |30| Packshot | `recommend` with the packshot need in the user's own words (a cutout-and-stage tool with solid, transparent, or custom backgrounds, margins, and shadows was the authoring-time hit), or background removal plus your own compose |31| Lifestyle scene | `recommend` with `capability="img2img"`, product photo as reference, preserve-first prompt, one scene per run |32| Relight | `search` `"relighting"` (the authoring-time hit adjusts light, exposure, and mood, with a brand-color lock) |33| Upscale keepers | `recommend` with the user's own words; product-tuned upscalers existed at authoring time |34| Gate | `asset_analyze` the outputs against the checklist: up to 10 ids in `images`, the saved checklist in `text_inputs`, the letter-by-letter brief in `instruction` |3536## The preserve-first prompt3738Scene prompts subordinate the world to the product: "The exact can from the reference image,39proportions and colors unchanged, the label reads 'SUMMIT COLD BREW', no other text, standing on a40wet slate counter, morning side light, shallow depth of field." Name the placement, the surface, the41light. What goes unstated drifts: "label unchanged" alone leaves the type to whatever the model42resolves from the reference, so the preserve clause quotes the checklist's label copy (existing43on-pack text only) and the gate reads it back letter by letter rather than trusting the render.4445Shadows and reflections carry the realism: a cutout pasted without them floats. Prefer a stage tool46that rebuilds shadows, or name one in the edit prompt ("soft contact shadow falling right").4748## Worked example: one can, a packshot plus three scenes49501. `upload_asset` the studio photo, then `upload_asset_complete`: `asset_can`.512. Build the checklist once with `asset_analyze` (write lane, contract in52 `scenario-asset-analysis`); the inventory lands as a text asset, so `asset_download` it and keep53 the text.543. Packshot: `recommend` with the packshot need in the user's own words, `model_schema_get` the55 pick, then run it with `asset_can` in its image field, the background set to the brand hex, and56 margins per the marketplace's current spec (confirm specs with the user; unattended, take them57 from the task instructions, else keep the tool's defaults).584. Scenes: `recommend` with `capability="img2img"`; on `next_step.type="ask_user"`, present the59 options (unattended, the task instructions name the pick, else `proceed`: `specialty.model_id`60 first, skipping a specialty whose `caveats` or `when_general_better` name the task at hand, then61 the top `ranked` entry, never one flagged `requires_plan_upgrade`). `model_schema_get` the pick,62 then three runs, each the preserve-first prompt with one scene clause and `asset_can` wired as63 the schema says (an array only under `array: true`).645. `jobs_wait`, then gate all four outputs in one `asset_analyze` call, the saved checklist passed65 via `text_inputs` and an instruction to read the label back letter by letter. A drifted label66 fails the shot: re-run from `asset_can` with the preserve clause tightened (the quoted copy67 spelled letter by letter, "no other text" kept), never from the drifted output. Text the gate68 cannot resolve at output resolution is unverified, not passed: upscale and re-gate, or flag it in69 the delivery note.706. Upscale the keepers, `asset_download` with `format="png"`, file the set in a collection.7172## Common mistakes7374- Generating the product from a text description because the photo seems easy to describe: the one75 unfixable error, since no edit restores a label that never existed.76- Compositing from a screenshot of a crop: fidelity caps at the source; ask for the original file,77 and when nobody can supply one, proceed with the best source at hand and flag the ceiling in the78 delivery note.79- Skipping the gate because it "looks fine": label drift hides at thumbnail size; the checklist80 compare reads letter by letter.81- Prompting prices, claims, or promo copy into the image: overlay them with `scenario-text-overlay`;82 regulations and locales change faster than plates.83- Removing the background and losing the real shadow with it: restage with a shadow-building tool or84 prompt a new one.85- One run with a batch count for "the same scene, four angles": per-angle clauses need one run each86 (`scenario-image`).