Create a transition from first and last frames

Prepare two compatible compositions

Use similar camera positions, perspective and subjects. For an interior transformation, keep walls and windows aligned while changing furniture. Large viewpoint differences make a clean transition harder.

Describe the bridge between the images

Tell the model how to move from the opening toward the ending: furniture gradually appears and settles, with a fixed camera and consistent daylight. Two inputs alone do not explain the intended action.

Inspect the middle as well as the endpoints

Watch for warped geometry, floating objects and sudden changes. The model can reinterpret both inputs; it is not simply replaying them pixel for pixel. Exact intermediate and final frames are not guaranteed.

Split difficult transitions

If the change is too large, create smaller transitions with compatible reference frames and edit the shots together. The public interface does not offer one-click video extension or a precise motion-path editor.

Settings and credit budget

Choose 5, 10 or 15 seconds. Text tasks cost 6 credits; image and two-frame tasks cost 8. New Google accounts receive a one-time 60-credit grant valid for 30 days. Landscape output is 896 × 512 and portrait output is 512 × 896 at 24 fps. Each account can have one active task. Wait for a confirmed result instead of repeatedly submitting.

从这个提示词开始

人物轻轻眨眼并自然微笑，轻微呼吸，微风吹动几缕头发，头部基本不动，固定镜头，一个连续镜头。

可从这个提示词开始，每次只调整一个动作或镜头指令。它是提示词示例，不是对特定成片效果的承诺。