Generation modes and drafting

Text-to-video, image-to-video, multi-reference, first/last frame, and extend do not all need the same kind of information.

ModeWhat the prompt should prioritizeCommon failure
Text to videoComplete but compact shot layersToo many events packed into one clip
Image to videoPreserve @Image1 and only add motion plus necessary light changeRe-describing the still until face or product drifts
Video to videoTransfer motion, camera, and rhythmCopying a likeness that should not be copied
Multi-referenceOne clear role per assetOne image controlling identity, pose, and style at once
First / last frameA continuous path from the first frame to the lastWriting the last frame as a vague mood instead of an end state
ExtendContinue only from an accepted real endingBlind-extending the original prompt

A common fidelity line for image-to-video

@Image1 is the product reference; preserve label, logo, shape, and color exactly. Only motion changes: …

Browse prompt cases