minimax/h3-max/camera-controls
Text prompt for video generation. When omitted or blank, defaults to preserving the frozen reference scene while only the camera moves.
URL of the image to use as the first frame.
The duration of the video in seconds.
How much effort to spend rewriting the prompt before generation. 'disabled' skips prompt expansion. 'balanced' returns in about a second. 'quality' spends up to ~30s on a richer prompt.
Run the model to see the result here.