Vidu Commands & Prompt Reference
24 commands & parameters · 3 categories · Source: Vidu Platform API Docs
Vidu's generation API is a flat JSON body rather than a typed content tree: you pick a model, write a prompt of up to 5000 characters, and shape the output through duration, resolution, aspect ratio, seed, and movement amplitude. Three endpoints share most of that vocabulary - text to video, image to video, and reference to video - so the parameters on this page apply across all three unless a field is endpoint-specific.
Two details save time. Defaults vary by model rather than being global: duration and resolution ranges differ between viduq1, viduq2, and the q3 pair, and the style parameter has no effect on q2 or q3. And off_peak mode trades latency for cost, which matters for batch work more than for interactive generation.
All Commands
Generation Parameters (14)
| Command / Syntax | What it does | Notes |
|---|---|---|
| model | Model name | Accepted values:viduq3-turbo, viduq3-pro , viduq2 , viduq1 -viduq3-turbo: Compared to viduq3-pro, the generation speed is faster -viduq3-pro: Supports audio-visual synchronization,... Required. |
| style | The style of output video | Defaults to general, Accepted values: general anime - general : General style. Allows style control through prompts - anime: Anime style. Optimized for anime aesthetics, with better... |
| prompt | Text prompt A textual description for video generation, with a maximum length of 5000 characters | Required. |
| duration | Video duration | Default values vary by model: - viduq3-pro,viduq3-turbo: default 5s, available: 1 - 16 - viduq2: default 5s, available: 1 - 10 - viduq1: default 5s, available: 5 |
| seed | Random seed - | Defaults to a random seed number - Manually set values will override the default random seed |
| aspect_ratio | The aspect ratio of the output video | Defaults to 16:9, accepted: 16:9 9:163:4 4:3 1:1 Note:3:4& 4:3only support q2 & q3 model |
| resolution | Resolution | Default values vary by model & duration: - viduq3-pro , viduq3-turbo (1-16s): default 720p, available: 540p, 720p, 1080p - viduq2 (1-10s): default 720p, available: 540p 720p 1080p -... |
| movement_amplitude | The movement amplitude of objects in the frame | Defaults to auto, accepted value: auto small medium large This parameter does not take effect when using the q2 & q3 model |
| images | An image to be used as the start frame of the generated video For fields that accept images: - Only accepts 1 image -... | - Supported formats: png, jpeg, jpg, webp - The aspect ratio of the images must be less than 1:4 or 4:1 - All images are limited to 50MB - The post body of the HTTP request should not... Required. |
| voice_id | Voice ID, The Q3 series model is not effective Used to determine the voice character in the video | The system will automatically recommend a suitable voice, and optional values can be found in the Voice List. You can also use the Voice Cloning API to clone any voice. The voice_id... |
| is_rec | Whether to use the recommended prompt | - true: Yes, the system will automatically generate and apply a recommended prompt to create the video. The number of recommended prompts = 1. - false: No, the video will be generated... |
| auto_subjects | Optional | Whether to use the intelligent entity library capability, default is false, optional values are true and false... | - false: Do not use the intelligent agent library capability. |
| subjects | Required | When using the q3, q2, q1, and 2.0 models, only the main body of the image and text can be used - The maximum... | JSON body field of the Vidu generation endpoints. |
| videos | Optional | The video URL corresponding to the subject | All subjects share a 13s duration (each image subject = 1s). Must provide either this or images. - Note 1: This parameter is only supported by the viduq2-pro model. - Note 2: When using... |
Task & Delivery Parameters (6)
| Command / Syntax | What it does | Notes |
|---|---|---|
| bgm | Whether to add background music to the generated video.（q3 model not available） Default: false | Acceptable values: true, false. When true, the system will automatically add a suitable BGM. BGM has no time limit and the system automatically adapts. BGM does not take effect when the... |
| audio | Whether to use direct audio-video generation capability | Default: true. Enumerated values: - false: No direct audio-video generation, outputs silent video - true: Requires audio-video synchronization, outputs video with sound (including... |
| payload | transparent transmission parameters No processing, only data transmission，with a maximum length of 1048576 characters | JSON body field of the Vidu generation endpoints. |
| off_peak | off peak mode, | Defaults to false, accepted value: true false - true：off peak generate mode； - false：normal generate mode； - The off_peak mode consumes lower points, please refer to the details Pricing.... |
| callback_url | Callback When creating a task, you need to actively set the callback_url with a POST request | When the video generation task changes its status, Vidu will send a callback request to this URL, containing the latest status of the task. The structure of the callback request content... |
| audio_type | Audio type, required when audio is true, defaults to all -All: Sound effects+vocals -Speech_only: Vocal only... | JSON body field of the Vidu generation endpoints. |
Model IDs (4)
| Command / Syntax | What it does | Notes |
|---|---|---|
| viduq3-pro | Model ID with audio-visual synchronization and video shot segmentation | Set as the model field value. |
| viduq3-turbo | Faster variant of viduq3-pro | Set as the model field value. |
| viduq2 | Second-generation Vidu model ID | Supports 3:4 and 4:3 aspect ratios; duration 1-10s. |
| viduq1 | First-generation model: clear image, smooth transition, stable camera | Fixed 5s duration at 1080p. |
Frequently Asked Questions
Which Vidu model should I pick?
viduq3-pro supports audio-visual synchronization and shot segmentation; viduq3-turbo trades some of that for speed; viduq2 is the newer general model; viduq1 is fixed at 5 seconds and 1080p.
How long can a generated video be?
It depends on the model: the q3 pair accepts 1-16 seconds, viduq2 accepts 1-10, and viduq1 is fixed at 5. All default to 5 seconds.
How do I get the result?
Generation is asynchronous. Set callback_url when creating the task to be notified on status changes, or poll the task endpoint.
Every entry on this page is a literal, typeable token taken from the official documentation linked above. Command sets in AI tools change quickly - the in-product command menu is always authoritative for your installed version.
Prompting for motion
Vidu generates short clips from text or from a reference image, and the parameters in the table set duration, resolution, aspect ratio and motion strength. Image-to-video works best when the prompt describes what should change rather than restating what the image shows; text-to-video needs subject, action, environment and a camera note in that order. Reference-to-video, Vidu's multi-image consistency feature, keeps a character stable across shots and is the reason to use Vidu for a sequence rather than a single clip.
Iterating
Fix the seed once a composition works and vary one phrase at a time; motion strength is the parameter to lower when a clip warps, and duration the one to shorten when detail degrades. The API and web app share parameter names, and the prompts and answers here are checked against Vidu's current documentation on the date shown.