API Version 2024-11-06
The 2024-11-06 API version introduces changes to the /v1/image_to_video endpoint.
The ratio parameter no longer accepts 16:9 and 9:16. Instead, it now accepts the
resolution for the output video directly. The accepted values are:
1280:768768:1280
These new values will be accepted by the previous API version (2024-09-13), allowing
you to incrementally upgrade, however be aware that this older API version will be phased
out over time.
promptImage
Section titled “promptImage”The promptImage parameter was previously defined as a string. It is now equivalent to
the following:
type promptImage = | string | Array<{ uri: string; position: 'first' | 'last'; }>;from typing import Union, List, Literal, TypedDict
class ImagePosition(TypedDict): uri: str position: Literal['first', 'last']
PromptImage = Union[str, List[ImagePosition]]The following two are equivalent:
{ "promptImage": "https://example.com/image.jpg"}{ "promptImage": [ { "uri": "https://example.com/image.jpg", "position": "first" } ]}If you were to set position to "last", the generated video will end with
the image instead of starting with it.
{ "promptImage": [ { "uri": "https://example.com/image.jpg", "position": "last" } ]}You can also pass two images to the promptImage parameter:
{ "promptImage": [ { "uri": "https://example.com/image1.jpg", "position": "first" }, { "uri": "https://example.com/image2.jpg", "position": "last" } ]}In the above example, the generated video will start with image1.jpg and
end with image2.jpg.
The maximum value of seed is now 4294967295 (or 2^32 - 1), up from 999999999.