VIDU Q2 Text to Video
Video Generator
VIDU Q2 Text to Video
POST
VIDU Q2 Text to Video
VIDU Q2 Text to Video API, supports multiple resolution options. Generates video content based on text descriptions.Documentation Index
Fetch the complete documentation index at: https://novita.ai/docs/llms.txt
Use this file to discover all available pages before exploring further.
Request Headers
Supports:
application/jsonBearer authentication format, for example: Bearer {{API Key}}.
Request Body
Whether to add background music
Random seed, used to control the randomness of the generation result. The same seed will produce similar results.
Whether to generate audio
Video style, e.g., cinematic, realistic, artistic, etc.
Text prompt, describing the desired video content in detailLength limit: 1 - unlimited
Video duration in seconds, supports 1-10 secondsOptional values:
1, 2, 3, 4, 5, 6, 7, 8, 9, 10List of subjects, each containing id, images, and voice_id (can be empty for text-to-video)
Whether to add watermark
Output video resolution. Default is 720p.Optional values:
540p, 720p, 1080pVideo aspect ratio, e.g., 16:9, 9:16, 1:1, etc.
Movement amplitude, controls the intensity of object movement in the videoOptional values:
auto, small, medium, highResponse
Use the task_id to request the Task Result API to retrieve the generated outputs.