Veo 3.1 Fast First/Last Frame Video Generation
Video
Veo 3.1 Fast First/Last Frame Video Generation
POST
Veo 3.1 Fast First/Last Frame Video Generation
Generate a video by specifying first-frame and last-frame images together with a text prompt. The model interpolates between the two frames to generate coherent motion content. Uses the Google Veo 3.1 Fast model (
veo-3.1-fast-generate-001) for faster generation.
Request Headers
string
required
Enum value:
application/jsonstring
required
Bearer authentication format: Bearer {{API key}}.
Request Body
integer
Random seed for deterministic generation. The same seed and parameters will produce the same result.Value range: [0, 4294967295]
string
required
First-frame image, supporting image URLs or Base64 encoding. Supports JPEG and PNG formats, up to 20MB.
string
required
Text prompt describing the video content and the motion process between the first and last frames.
string
required
Last-frame image, supporting image URLs or Base64 encoding. Supports JPEG and PNG formats, up to 20MB.
string
default:"720p"
Output video resolution.Allowed values:
720p, 1080pstring
default:"16:9"
Video aspect ratio. 16:9 is landscape, and 9:16 is portrait.Allowed values:
16:9, 9:16integer
default:1
Number of videos to generate, ranging from 1 to 4.Value range: [1, 4]
boolean
default:true
Whether to enhance the input prompt to improve generation quality.
boolean
default:false
Whether to generate an audio track.
string
Negative prompt describing content you do not want to appear in the video.
integer
default:8
Video duration in seconds. Options: 4, 6, or 8 seconds.Allowed values:
4, 6, 8string
default:"allow_adult"
Person generation control. allow_adult: allow generating adults; disallow: prohibit generating people.Allowed values:
allow_adult, disallowResponse Information
string
Use task_id to request the Get Task Result API to retrieve the generated output.