Vidu Video
The Vidu video series currently provides three integration methods: the official format (/vidu/ent/v2/*), OpenAI-compatible /v1/videos (multipart/form-data format), and the unified video endpoints /v1/video/create and /v1/video/query (JSON).
Official Format
Use the/vidu/ent/v2/* series of interfaces, which support multiple video generation modes.
Text to Video
POST /vidu/ent/v2/text2video, generates video from text only.Image to Video
POST /vidu/ent/v2/img2video, generates video from a first-frame image.Start-End Frame to Video
POST /vidu/ent/v2/start-end2video, generates video from start and end frames.Reference to Video
POST /vidu/ent/v2/reference2video, generates video with subject reference.Query Task
GET /vidu/ent/v2/task/{task_id}/creations, queries task status and results.Supported Models (Official Format)
| Model | Description | Duration Rules |
|---|---|---|
viduq3-pro | Efficiently generates high-quality audio and video content | Depends on the model |
viduq2 / viduq2-pro | New model with good results and rich details | 1-10 seconds |
viduq2-turbo | New model with good results and fast generation | 1-10 seconds |
viduq1 / viduq1-classic | Clear visuals and smooth transitions | Depends on the model |
vidu2.0 | Fast generation speed | Depends on the model |
OpenAI Format
UsePOST /v1/videos to submit and GET /v1/videos/{task_id} to query, with submission in multipart/form-data.
Video Generation
POST /v1/videos, submits a Vidu video task.Task Status Query
GET /v1/videos/{task_id}, queries task status and results.Supported Models (OpenAI Format)
| Model | Description |
|---|---|
viduq3-pro | Efficiently generates high-quality audio and video content, making the video more vivid, more expressive, and more immersive |
viduq2-pro | New model with good results and rich details |
viduq2-turbo | New model with good results and fast generation |
Unified Video
UsePOST /v1/video/create to create tasks, and GET /v1/video/query?id= for queries.
Generate Video
POST /v1/video/create, submits a Vidu task in the unified video format.Query Task
GET /v1/video/query, queries status and results by task id.Common Capabilities (Unified Video)
| Capability | Parameter Passing | Description |
|---|---|---|
| Text to Video | images: [] | Text prompt only |
| First-Frame to Video | images 1 image | First-frame image + text prompt |
| Start-End Frame to Video | images 2 images | First frame + end frame |
| Reference to Video | subjects array | Subject reference images |
Comparison
| Item | Official Format | OpenAI Format | Unified Video |
|---|---|---|---|
| Create | /vidu/ent/v2/* | POST /v1/videos | POST /v1/video/create |
| Query | GET /vidu/ent/v2/task/{task_id}/creations | GET /v1/videos/{task_id} | GET /v1/video/query?id= |
| Request Format | JSON | multipart/form-data | JSON |
| Reference Images | images / subjects | images | images |
| Aspect Ratio | aspect_ratio | aspect_ratio | aspect_ratio |
| Resolution | resolution | resolution | size |
| Duration | duration | duration | duration |
Parameter Constraints
| Field | Available Values | Description |
|---|---|---|
aspect_ratio | 16:9, 9:16, 3:4, 4:3, 1:1 | 3:4 and 4:3 are supported only by q2 and q3 models |
resolution | 540p, 720p, 1080p | Resolution specification |
duration | 1-10 | Video duration (seconds), q2 defaults to 5 |
style | general, anime | Style (not effective for q2, q3) |
Featured Capabilities
| Feature | Description |
|---|---|
| Audio and Video Output | audio: true, outputs videos with dialogue and sound effects (q3 only) |
| Background Music | bgm: true, automatically adds BGM |
| Off-Peak Mode | off_peak: true, generates during off-peak times for lower credits |
| Recommended Prompts | is_rec: true, the system automatically recommends prompts |
| Watermark | watermark: true, adds a fixed watermark |
Related Pages
- Video Model Support Matrix
- Text to Video (Official Format)
- Image to Video (Official Format)
- Start-End Frame to Video (Official Format)
- Reference to Video (Official Format)
- Query Task (Official Format)
- Video Generation (OpenAI Format)
- Task Status Query (OpenAI Format)
- Generate Video (Unified Video)
- Query Task (Unified Video)