Image-to-Video (I2V) — Generative AI glossary — LiliDi
Generate a short video clip starting from a single still image plus a motion prompt.
By LiliDi Editorial
Generate a short video clip starting from a single still image plus a motion prompt. Image to Video (I2V) is a generative pipeline where a still image is used as the first frame of a 3–10 second video clip, and a text prompt describes camera movement, character action and ambience. Kling 3.0, Veo 3.1, Runway Gen 4 and Seedance 2.0 all support I2V. Best for animating product shots, character keyframes and storyboards. Related: text to video, end frame, motion prompt.