Home/VIDU Q2 Text to Video
Vidu

VIDU Q2 Text to Video

Video
Model API docs

Vidu is built for speed and controllable shots (e.g., keyframes), keeping narratives coherent for rapid iteration. Vidu Q2 offers multiple control modes (templates, first/last frames, multi‑frame) for coherent storytelling. Text Instant inference API, stable performance, no waiting, budget-friendly.

0 / 2000
Pending
Empty state

Set parameters and click Generate to get results

Examples

Request JSON

{}

API

Submit task

curl --location --request POST 'https://api.novita.ai/v3/async/vidu-q2-text2video' \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${API_KEY}" \
--data-raw '{}'

Query result

curl --location --request GET "https://api.novita.ai/v3/async/task-result?task_id
=${task_id}" \
--header "Authorization: Bearer ${API_KEY}"