Text → Image → Video Pipeline

Two-stage chain. Stage 1 produces a still you can iterate on cheaply; stage 2 animates the chosen still.

When to use

• The shot needs a specific composition or character pose locked before motion.
• Direct text-to-video drifts off-prompt; this gives you an anchor frame.
• Cost: one image gen + one video gen per accepted take. Iterating on the still is cheap; iterating on motion is not — get the still right first.

Inputs

• A shot brief from scripts/storyboards/NN-*.md (visual prompt seed, duration, character refs).
• Model selection from brief/tools-and-models.md (text-to-image model + image-to-video model).
• Optional: character reference image from characters/<name>.md.

Steps