Video
Image-to-video
Image-to-video animates a still image into a video clip: the picture fixes the subject and framing, and a prompt describes the motion. It is the standard way to keep a specific face or product consistent in generated video.
Because the reference image carries identity, composition and style, the prompt only has to direct movement — a turn, a breeze, a push-in. Some engines accept both a start frame and an end frame and interpolate between them, which gives precise control over where a clip ends.
On eroq
Every video engine accepts a start image; Seedance 2.5 also takes an end frame. Sources are a photo, a render from the image studio (press Animate) or a saved Character.
Questions
Does image-to-video keep the face?
Yes — that is its purpose. Kling and Seedance hold identity especially well through motion.
Should the prompt describe the image again?
No — describe only what moves. Re-describing the subject fights the reference.
More video terms