Stage Consistency

stage-consistency

How to keep characters, settings, and style consistent across many generated shots (and across scenes in a long story). This is the depth layer on top of the generation line: the generation line makes clips; this skill makes the SAME character look the same in every clip. Describe the outcome; the tools are ovs image for portraits (incl. reference-image editing), ovs video for image-to-video, ovs edit extract-frame to pull an anchor frame, and a long-document strategy (chunking + retrieval/RAG over the source) for long sources (or the equivalent MCP tools).

1. Character bible (extract once, lock the look)

From the script/idea, extract every recurring character into project/characters/bible.json. For each character separate:

• static features — the immutable visual identity: face, hair, body shape, ethnicity, age range. These NEVER change shot-to-shot.
• dynamic features — changeable: clothing, accessories, expression.
• a single canonical name (merge every alias/pronoun for the same person to one id).

{
  "alice": {
    "static": "early-20s East-Asian woman, oval face, long black hair, slim build",
    "dynamic": "green linen dress, small gold earrings",
    "portrait": { "front": "characters/alice_front.png", "side": "characters/alice_side.png", "back": "characters/alice_back.png" }
  }
}

2. Portrait anchor (generate once, then LOCK)

For each character, generate ONE front portrait (full-body, front view, plain background) from its static+dynamic features with ovs image. This is the anchor — never regenerate it. Derive side/back views by reference-image editing the front portrait (so all three views are the same person). Save paths into the bible.

• Cameo (the user uploads a photo to BE a character): use that photo AS the front portrait — skip generation for that character. Everything downstream references it.

3. Storyboard with character binding

Decompose the script into shots. Each shot records:

• which characters are visible (and at what camera angle — front / side / back),
• a first-frame description and the motion,
• describe motion by VISUAL FEATURES, not names — write "the figure in the green dress turns to the figure in the blue shirt", NOT "Alice turns to Bob". (Generators ground on appearance, not names.)

4. Per-shot reference selection (the core consistency mechanism)

For each shot, before generating it, assemble the reference images and bind them explicitly:

1. Candidates = for every visible character, the portrait view that MATCHES the shot's camera angle (front shot → front portrait, profile → side portrait) plus the most recent already-generated frame that shares this scene/camera.
2. Priority: a recent prior frame of the same camera > an older frame > portrait-only; same-camera > different-camera. Keep relative positions (if a character was on the left, keep them on the left). Don't pick two references that show the same face.
3. Explicit binding: write a generation prompt that maps each reference to what it's for — "ref 1 (front portrait) → facial features & hair; ref 2 (previous frame) → lighting & background".
4. Generate the shot with ovs video image-to-video using those reference images.

4b. Verify the keyframe BEFORE you pay to animate

For a character-critical shot, generate the first-frame image first (cheap), check it, and only then drive the video from that locked frame — catching drift at the still is far cheaper than discovering it after paying to animate.

• Check the keyframe against the bible on the identity axes, in priority order: 1) character — gender, age, ethnicity, facial features, body shape, hairstyle; 2) spatial — relative positions/perspective match the reference (left stays left); 3) accuracy — matches the shot's description. Read it yourself if multimodal; if you cannot see images, mark it unverified and lean harder on a strong locked reference.
• Re-roll the cheap image, not the expensive video, until it matches; generate a few candidates and keep the most consistent one. Never hard-fail — pick the best and note its shortcoming.