scenario-consistency
Scenario Consistency
Overview
"Make variant two look exactly like variant one except for X" is the most repeated creative ask, and agents reach for seeds, which do not solve it. Consistency comes from what you feed the model, in rising order of durability: a prompt baseline, reference images, a style reference, a control map, a trained model. The same references carry a character into video. Connection and the core loop: see the scenario skill; training: see scenario-model-training; creating and filing a named character or prop library, with its sheets: see scenario-identity-library. If a sibling skill named here is missing from your available skills, ask the user to install it (npx skills add scenario-labs/skills --skill <name>); unattended, proceed from tool schemas and flag the gap.
Quick reference
| Technique | Holds | Effort | Reach for it when |
|---|---|---|---|
| Baseline-plus-delta prompt | identity, framing, palette | low | always, it is the floor |
| Reference image input | identity and world | low | a set of scenes or angles |
| Style reference input | rendering style, not a subject | low | icon sets, UI, an illustration series |
asset_detect control map |
pose, geometry, composition | medium | the layout must not move |
| Reference-to-video | identity through motion | medium | the character or product has to move |
| Seed reuse | one image's exact roll | low | re-rolling a single generation |
| Trained model | a house style, or a cast at scale | high | references stop scaling (see below) |
Scenario's published pipeline guidance: generate one strong reference image, pass it as an image input to every scene generation, and prefer models with the most reference-image slots.