> For the complete documentation index, see [llms.txt](https://docs.console.zenlayer.com/api/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.console.zenlayer.com/api/compute/aig/video-generation/vidu/create-video.md). # Create Video Generation Task ## 1. Overview Vidu is China's first long-duration, high-consistency, high-dynamics video large model, officially released by Shengshu Technology in collaboration with Tsinghua University. Vidu has leading advantages in semantic understanding, inference speed, and motion amplitude, and has launched the world's first "multi-subject reference" feature, breaking through the consistency generation challenge of video models and ushering in the era of visual context. Call the Create Video Generation Task API to obtain the returned video task `task_id` field, then copy it to the [Query API](/api/compute/aig/video-generation/vidu/fetch-video.md) to query and download the video. **Model List:** * `viduq3-pro` * `viduq3-pro-fast` * `viduq3-turbo` * `viduq3-mix` * `viduq3` * `viduq2-pro` * `viduq2-pro-fast` * `viduq2` * `vidu2.0` * `viduq1` * `viduq1-classic` {% hint style="info" %} For Vidu series models, we fully align with the official credits field (returned by the API) for billing. For detailed credits consumption rules of each model, refer to the [official documentation](https://platform.vidu.com/docs/pricing). {% endhint %} ## 2. Request Description * **Request Method**:`POST` * **Text-to-Video URL**: > `https://gateway.theturbo.ai/v1/vidu/text2video` * **Image-to-Video URL**: > `https://gateway.theturbo.ai/v1/vidu/img2video` * **Start-End Frame-to-Video URL**: > `https://gateway.theturbo.ai/v1/vidu/start-end2video` *** ## 3. Request Parameters ### 3.1 Header Parameters | Parameter Name | Type | Required | Description | Example | | --------------- | ------ | -------- | ------------------------------------------------------------------- | ---------------------- | | `Content-Type` | string | Yes | Set the request header type, must be `application/json` | `application/json` | | `Accept` | string | Yes | Set the response type, recommended to use `application/json` | `application/json` | | `Authorization` | string | Yes | API\_KEY required for authentication, format `Bearer $YOUR_API_KEY` | `Bearer $YOUR_API_KEY` | *** ### 3.2 Body Parameters (application/json) #### Text-to-Video Parameters | Parameter Name | Type | Required | Description | Example (Default) | | ------------------- | ------ | -------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------- | | **model** | string | Yes | Model name, see Model List | `viduq3-turbo` | | style | String | Yes | Style. `general`: general style, style can be controlled via prompts. `anime`: anime style, excels only in anime style, can be controlled with different anime style prompts | `general` | | prompt | String | Yes | Text prompt. Note: character length cannot exceed 5000 characters | | | duration | Int | No | Video duration parameter, default 5 seconds, options: 1-16 | | | seed | Int | No | Random seed | | | aspect\_ratio | String | No | Aspect ratio. Options: `16:9`, `9:16`, `3:4`, `4:3`, `1:1` | `16:9` | | resolution | string | No | Resolution parameter. Options: `540p`, `720p`, `1080p` | `720p` | | movement\_amplitude | string | No | Movement amplitude. Options: `auto`, `small`, `medium`, `large` | `auto` | | bgm | string | No | Whether to add background music to the generated video. When set to true, the system will automatically select suitable music from the preset BGM library and add it; when not set or set to false, no BGM will be added. | `false` | | audio | string | No | Whether to use audio-video direct output capability. - false: no audio-video direct output, outputs silent video - true: requires audio-visual synchronization, outputs video with sound (including dialogue and sound effects) | `true` | | watermark | string | No | Whether to add a watermark. - true: add watermark; - false: do not add watermark; | false | | wm\_position | string | No | Watermark position, indicates where the watermark appears on the image. Options: 1: top-left 2: top-right 3: bottom-right 4: bottom-left | `3` | | wm\_url | string | No | Watermark content, this is an image URL. When not provided, the default watermark is used: "Content generated by AI" | | | meta\_data | string | No | Metadata identifier, JSON format string, pass-through field. You can customize the format or use the example format as follows: {"Label": "your\_label","ContentProducer": "your\_content\_producer","ContentPropagator": "your\_content\_propagator","ProduceID": "your\_product\_id","PropagateID": "your\_propagate\_id","ReservedCode1": "your\_reserved\_code1","ReservedCode2": "your\_reserved\_code2"} When this parameter is empty, the metadata identifier generated by Vidu will be used by default | | #### Image-to-Video Parameters | Parameter Name | Type | Required | Description | Example (Default) | | ------------------- | -------------- | -------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------- | | **model** | string | Yes | Model name, see Model List | `viduq3-turbo` | | images | Array\[String] | Yes | First frame image. The model will use the image passed in this parameter as the first frame to generate the video. Supports passing image Base64 encoding or image URL (must be accessible). Only 1 image is supported. Image formats supported: png, jpeg, jpg, webp; image aspect ratio must be less than 1:4 or 4:1; image size must not exceed 50 MB. Note that the HTTP request POST body must not exceed 20MB, and the encoding must include the appropriate content type string data:image/png;base64,{base64\_encode} | | | prompt | String | Yes | Text prompt. Note: character length cannot exceed 5000 characters | | | audio | string | No | Whether to use audio-video direct output capability. - false: no audio-video direct output, outputs silent video - true: requires audio-visual synchronization, outputs video with sound (including dialogue and sound effects) | `true` | | voice\_id | string | No | Used to determine the voice timbre in the video. When empty, the system will automatically recommend one | `true` | | bgm | string | No | Whether to add background music to the generated video. When set to true, the system will automatically select suitable music from the preset BGM library and add it; when not set or set to false, no BGM will be added. | `false` | | duration | Int | No | Video duration parameter, default 5 seconds, options: 1-16 | | | seed | Int | No | Random seed | | | aspect\_ratio | String | No | Aspect ratio. Options: `16:9`, `9:16`, `3:4`, `4:3`, `1:1` | `16:9` | | resolution | string | No | Resolution parameter. Options: `540p`, `720p`, `1080p` | `720p` | | movement\_amplitude | string | No | Movement amplitude. Options: `auto`, `small`, `medium`, `large` | `auto` | | watermark | string | No | Whether to add a watermark. - true: add watermark; - false: do not add watermark; | false | | wm\_position | string | No | Watermark position, indicates where the watermark appears on the image. Options: 1: top-left 2: top-right 3: bottom-right 4: bottom-left | `3` | | wm\_url | string | No | Watermark content, this is an image URL. When not provided, the default watermark is used: "Content generated by AI" | | | meta\_data | string | No | Metadata identifier, JSON format string, pass-through field. You can customize the format or use the example format as follows: {"Label": "your\_label","ContentProducer": "your\_content\_producer","ContentPropagator": "your\_content\_propagator","ProduceID": "your\_product\_id","PropagateID": "your\_propagate\_id","ReservedCode1": "your\_reserved\_code1","ReservedCode2": "your\_reserved\_code2"} When this parameter is empty, the metadata identifier generated by Vidu will be used by default | | #### Start-End Frame-to-Video Parameters | Parameter Name | Type | Required | Description | Example (Default) | | ------------------- | -------------- | -------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------- | | **model** | string | Yes | Model name, see Model List: viduq3-turbo, viduq3-pro, viduq2-pro-fast, viduq2-pro, viduq2, viduq1, vidu2.0, viduq1-classic | `viduq3-turbo` | | images | Array\[String] | Yes | Supports two input images. The first uploaded image is treated as the first frame, and the second image is treated as the last frame. The model will use these images to generate the video. | | | prompt | String | Yes | Text prompt. Text description for generating the video. | | | is\_rec | bool | No | Whether to use recommended prompts | | | duration | int | No | Video duration parameter, default 5 seconds, options: 1-16 | | | seed | int | No | Random seed | | | resolution | string | No | Resolution parameter. Options: `540p`, `720p`, `1080p` | `720p` | | movement\_amplitude | string | No | Movement amplitude. Options: `auto`, `small`, `medium`, `large` | `auto` | | audio | bool | No | Whether to use audio-video direct output capability. - false: no audio-video direct output, outputs silent video - true: requires audio-visual synchronization, outputs video with sound (including dialogue and sound effects) | `true` | | bgm | bool | No | Whether to add background music to the generated video. When set to true, the system will automatically select suitable music from the preset BGM library and add it; when not set or set to false, no BGM will be added. | `false` | | off\_peak | bool | No | Off-peak mode, default: false. Options: true: off-peak video generation, false: instant video generation | `false` | | watermark | bool | No | Whether to add a watermark. - true: add watermark; - false: do not add watermark; | false | | wm\_position | int | No | Watermark position, indicates where the watermark appears on the image. Options: 1: top-left 2: top-right 3: bottom-right 4: bottom-left | `3` | | wm\_url | string | No | Watermark content, this is an image URL. When not provided, the default watermark is used: "Content generated by AI" | | | meta\_data | string | No | Metadata identifier, JSON format string, pass-through field. You can customize the format or use the example format as follows: {"Label": "your\_label","ContentProducer": "your\_content\_producer","ContentPropagator": "your\_content\_propagator","ProduceID": "your\_product\_id","PropagateID": "your\_propagate\_id","ReservedCode1": "your\_reserved\_code1","ReservedCode2": "your\_reserved\_code2"} When this parameter is empty, the metadata identifier generated by Vidu will be used by default | | ## 4. Request Examples {% tabs %} {% tab title="Text to Video" %} ```sh curl https://gateway.theturbo.ai/v1/vidu/text2video \ -H "Content-Type: application/json" \ -H "Accept: application/json" \ -H "Authorization: Bearer $YOUR_API_KEY" \ -d '{ "model": "viduq3-pro", "style": "general", "prompt": "In an ultra-realistic fashion photography style featuring light blue and pale amber tones, an astronaut in a spacesuit walks through the fog. The background consists of enchanting white and golden lights, creating a minimalist still life and an impressive panoramic scene.", "duration": 5, "seed": 0, "aspect_ratio": "4:3", "resolution": "540p", "movement_amplitude": "auto", "off_peak": false }' ``` {% endtab %} {% tab title="Image to Video" %} ```sh curl https://gateway.theturbo.ai/v1/vidu/img2video \ -H "Content-Type: application/json" \ -H "Accept: application/json" \ -H "Authorization: Bearer $YOUR_API_KEY" \ -d '{ "model": "viduq3-pro", "images": ["https://****/image2video.png"], "prompt": "The astronaut waved and the camera moved up.", "audio": true, "voice_id": "professional_host", "duration": 5, "seed": 0, "resolution": "1080p", "movement_amplitude": "auto", }' ``` {% endtab %} {% tab title="Start-End Frame to Video" %} ```sh curl https://gateway.theturbo.ai/v1/vidu/start-end2video \ -H "Content-Type: application/json" \ -H "Accept: application/json" \ -H "Authorization: Bearer $YOUR_API_KEY" \ -d '{ "model": "viduq3-pro", "images": [ "https://***.jpeg", "https://****.jpeg" ], "prompt": "The camera zooms in on the bird, which then flies to the right. With its flight being smooth and natural, the bird soars in the sky. with a red light effect following and surrounding it from behind.", "duration": 5, "seed": 0, "resolution": "1080p", "audio": true, "off_peak": false }' ``` {% endtab %} {% endtabs %} ## 5. Response Example ```json { "aspect_ratio": "", "audio_type": "all", "client_request_id": "", "created_at": "2026-04-10T09:54:37.292958746Z", "credits": 12, "cus_priority": 0, "duration": 1, "images": [ "https://*****/image2video.png" ], "is_rec": false, "meta_data": "", "model": "viduq3-turbo", "movement_amplitude": "auto", "off_peak": false, "payload": "", "prompt": "The astronaut waved and the camera moved up.", "resolution": "720p", "seed": 366874707, "state": "created", "style": "general", "task_id": "940125400401448960", "type": "img2video", "watermark": false, "wm_position": "unspecified", "wm_url": "" } ``` --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.console.zenlayer.com/api/compute/aig/video-generation/vidu/create-video.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.