Vidu Q3 Turbo start-end-to-video generates high-quality videos from first and last frame images with text-guided motion interpolation, supporting up to 1080p resolution.
This is an asynchronous API; only the task_id will be returned. You should use the task_id to request the Task Result API to retrieve the video generation results.
Supports: application/json
Bearer authentication format, for example: Bearer {{API Key}}.
Request Body
Random seed for reproducibility. 0 means random.
Enable audio-video sync output (dialogue and sound effects). When false, output is silent video. Q3 series only.
Two image URLs or Base64 encoded images. First image as start frame, second as end frame. Supports png, jpeg, jpg, webp formats. Max 50MB per image. Both images must have similar resolution (ratio between 0.8-1.25). Aspect ratio must be < 1:4 or > 4:1.Array length: 2 - 2
Whether to use recommended prompt. When true, system auto-generates prompt.
Text description of desired video motion between start and end frames. Maximum 1500 characters.Length limit: 0 - 1500
Video duration in seconds, range 1-16.Value range: [1, 16]
Whether to use off-peak mode. Task will be processed within 48 hours at lower cost.
Output video resolution.Optional values: 540p, 720p, 1080p
Response
Use the task_id to request the Task Result API to retrieve the generated outputs.